Program | Technical Program

- Mon-O-1-1-1 (1746) Semi-Supervised End-to-End Speech Recognition
- Mon-O-1-1-2 (1616) Improved Training of End-to-end Attention Models for Speech Recognition
- Mon-O-1-1-3 (1423) End-to-end Speech Recognition Using Lattice-free MMI
- Mon-O-1-1-4 (1301) Multi-channel Attention for End-to-End Speech Recognition
- Mon-O-1-1-5 (1898) Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
- Mon-O-1-1-6 (1025) Compression of End-to-End Models

- Mon-O-1-2-1 (2075) Learning Interpretable Control Dimensions for Speech Synthesis by Using External Data
- Mon-O-1-2-2 (1227) Investigating Accuracy of Pitch-accent Annotations in Neural Network-based Speech Synthesis and Denoising Effects
- Mon-O-1-2-3 (1214) An Exploration of Local Speaking Rate Variations in Mandarin Read Speech
- Mon-O-1-2-4 (1472) BLSTM-CRF Based End-to-End Prosodic Boundary Prediction with Context Sensitive Embeddings in a Text-to-Speech Front-End
- Mon-O-1-2-5 (1499) Wavelet Analysis of Speaker Dependent and Independent Prosody for Voice Conversion
- Mon-O-1-2-6 (1706) Improving Mongolian Phrase Break Prediction by Using Syllable and Morphological Embeddings with BiLSTM Model

- Mon-O-1-3-1 (41) Improved Supervised Locality Preserving Projection for I-vector Based Speaker Verification
- Mon-O-1-3-2 (1103) Double Joint Bayesian Modeling of DNN Local I-Vector for Text Dependent Speaker Verification with Random Digit Strings
- Mon-O-1-3-3 (2128) Fast Variational Bayes for Heavy-tailed PLDA Applied to I-vectors and X-vectors
- Mon-O-1-3-4 (2289) Integrated Presentation Attack Detection and Automatic Speaker Verification: Common Features and Gaussian Back-end Fusion
- Mon-O-1-3-5 (1280) A Generalization of PLDA for Joint Modeling of Speaker Identity and Multiple Nuisance Conditions
- Mon-O-1-3-6 (2474) An Investigation of Non-linear I-vectors for Speaker Verification

- Mon-O-1-4-1 (1722) CNN Based Query by Example Spoken Term Detection
- Mon-O-1-4-2 (1010) Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search
- Mon-O-1-4-3 (1788) Siamese Recurrent Auto-encoder Representation for Query-by-Example Spoken Term Detection
- Mon-O-1-4-4 (1459) Fast Derivation of Cross-lingual Document Vectors from Self-attentive Neural Machine Translation Model
- Mon-O-1-4-5 (1016) LSTM Based Attentive Fusion of Spectral and Prosodic Information for Keyword Spotting in Hindi Language
- Mon-O-1-4-6 (1436) Spoken Keyword Detection Using Joint DTW-CNN

- Mon-SS-1-1-1 (51) The INTERSPEECH 2018 Computational Paralinguistics Challenge: Atypical & Self-Assessed Affect, Crying & Heart Beats
- Mon-SS-1-1-2 (-) Heart Beat Sub-Challenge
- Mon-SS-1-1-3 (2413) An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification
- Mon-SS-1-1-4 (-) Crying Sub-Challenge
- Mon-SS-1-1-5 (2187) Monitoring Infant’S Emotional Cry in Domestic Environments Using the Capsule Network Architecture
- Mon-SS-1-1-6 (1959) Neural Network Architecture That Combines Temporal and Summative Features for Infant Cry Classification in the Interspeech 2018 Computational Paralinguistics Challenge
- Mon-SS-1-1-7 (1914) Evolving Learning for Analysing Mood-Related Infant Vocalisation
- Mon-SS-1-1-8 (-) Atypical Affect Sub-Challenge
- Mon-SS-1-1-9 (1238) Deep Learning in Paralinguistic Recognition Tasks: Are Hand-crafted Features Still Relevant?
- Mon-SS-1-1-10 (1832) Investigation on Joint Representation Learning for Robust Feature Extraction in Speech Emotion Recognition
- Mon-SS-1-1-11 (1401) Using Voice Quality Supervectors for Affect Identification
- Mon-SS-1-1-12 (2581) An End-to-End Deep Learning Framework for Speech Emotion Recognition of Atypical Individuals

- Mon-S&T-1-1-1 (3002) DialogOS: Simple and extensible dialogue modeling
- Mon-S&T-1-1-2 (3003) A Framework for Speech Recognition Benchmarking
- Mon-S&T-1-1-3 (3004) Flexible tongue housed in a static model of the vocal tract with jaws, lips and teeth
- Mon-S&T-1-1-4 (3005) Voice Analysis Using Acoustic and Throat Microphones for Speech Therapy
- Mon-S&T-1-1-5 (3006) A Robust Context-Dependent Speech-to-Speech Phraselator Toolkit for Alexa

- Mon-P-1-1-1 (1032) Discriminating Nasals and Approximants in English Language Using Zero Time Windowing
- Mon-P-1-1-2 (1404) Gestural Lenition of Rhotics Captures Variation in Brazilian Portuguese
- Mon-P-1-1-3 (1958) Identification and Classification of Fricatives in Speech Using Zero Time Windowing Method
- Mon-P-1-1-4 (1185) GlobalTIMIT: Acoustic-Phonetic Datasets for the World’S Languages
- Mon-P-1-1-5 (1074) Structural Effects on Properties of Consonantal Gestures in Tashlhiyt
- Mon-P-1-1-6 (1457) The Retroflex-dental Contrast in Punjabi Stops and Nasals: a Principal Component Analysis of Ultrasound Images
- Mon-P-1-1-7 (1225) Vowels and Diphthongs in Hangzhou Wu Chinese Dialect
- Mon-P-1-1-8 (1176) Resyllabification in Indian Languages and Its Implications in Text-to-speech Systems
- Mon-P-1-1-9 (2352) Voice Source Contribution to Prominence Perception: Rd Implementation
- Mon-P-1-1-10 (2532) On the Relationship between Glottal Pulse Shape and Its Spectrum: Correlations of Open Quotient, Pulse Skew and Peak Flow with Source Harmonic Amplitudes
- Mon-P-1-1-11 (1649) The Individual and the System: Assessing the Stability of the Output of a Semi-automatic Forensic Voice Comparison System
- Mon-P-1-1-12 (2498) Breathy to Tense Voice Discrimination using Zero-Time Windowing Cepstral Coefficients (ZTWCCs)
- Mon-P-1-1-13 (1899) Analysis of Breathiness in Contextual Vowel of Voiceless Nasals in Mizo

- Mon-P-1-2-1 (2429) Infant Emotional Outbursts Detection in Infant-parent Spoken Interactions
- Mon-P-1-2-2 (2466) Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts
- Mon-P-1-2-3 (2478) Preference Learning with Qualitative Agreement for Sentence Level Emotional Annotations
- Mon-P-1-2-4 (1625) Transfer Learning for Improving Speech Emotion Classification Accuracy
- Mon-P-1-2-5 (1851) What Do Classifiers Actually Learn? a Case Study on Emotion Recognition Datasets
- Mon-P-1-2-6 (2043) State of Mind: Classification through Self-reported Affect and Word Use in Speech.
- Mon-P-1-2-7 (1477) Exploring Spatio-Temporal Representations by Integrating Attention-based Bidirectional-LSTM-RNNs and FCNs for Speech Emotion Recognition
- Mon-P-1-2-8 (2015) End-to-end Deep Neural Network Age Estimation
- Mon-P-1-2-9 (1462) Improving Gender Identification in Movie Audio Using Cross-Domain Data
- Mon-P-1-2-10 (1240) On Learning to Identify Genders from Raw Speech Signal Using CNNs
- Mon-P-1-2-11 (2321) Denoising and Raw-waveform Networks for Weakly-Supervised Gender Identification on Noisy Speech
- Mon-P-1-2-12 (2372) The Effect of Exposure to High Altitude and Heat on Speech Articulatory Coordination

- Mon-P-1-3-1 (1603) Permutation Invariant Training of Generative Adversarial Network for Monaural Speech Separation
- Mon-P-1-3-2 (1205) Deep Extractor Network for Target Speaker Recovery from Single Channel Speech Mixtures
- Mon-P-1-3-3 (1269) Joint Localization and Classification of Multiple Sound Sources Using a Multi-task Neural Network
- Mon-P-1-3-4 (1281) Detection of Glottal Closure Instants from Speech Signals: a Convolutional Neural Network Based Method
- Mon-P-1-3-5 (1652) Robust TDOA Estimation Based on Time-Frequency Masking and Deep Neural Networks
- Mon-P-1-3-6 (1671) Waveform to Single Sinusoid Regression to Estimate the F0 Contour from Noisy Speech Using Recurrent Deep Neural Networks
- Mon-P-1-3-7 (1845) Reducing Interference with Phase Recovery in DNN-based Monaural Singing Voice Separation
- Mon-P-1-3-8 (1258) Nebula: F0 Estimation and Voicing Detection by Modeling the Statistical Properties of Feature Extractors
- Mon-P-1-3-9 (2290) Real-time Single-channel Dereverberation and Separation with Time-domain Audio Separation Network
- Mon-P-1-3-10 (2326) Music Source Activity Detection and Separation Using Deep Attractor Network
- Mon-P-1-3-11 (2561) Improving Mandarin Tone Recognition Using Convolutional Bidirectional Long Short-Term Memory with Attention

- Mon-P-1-4-1 (68) Vowel Space as a Tool to Evaluate Articulation Problems
- Mon-P-1-4-2 (1054) Towards a Better Characterization of Parkinsonian Speech: a Multidimensional Acoustic Study
- Mon-P-1-4-3 (1125) Self-similarity Matrix Based Intelligibility Assessment of Cleft Lip and Palate Speech
- Mon-P-1-4-4 (1251) Pitch-Adaptive Front-end Feature for Hypernasality Detection
- Mon-P-1-4-5 (2389) Detection of Amyotrophic Lateral Sclerosis (ALS) via Acoustic Analysis
- Mon-P-1-4-6 (1665) Detection of Glottal Activity Errors in Production of Stop Consonants in Children with Cleft Lip and Palate

- Mon-O-2-1-1 (1392) Cold Fusion: Training Seq2Seq Models Together with Language Models
- Mon-O-2-1-2 (1766) Investigation on Estimation of Sentence Probability by Combining Forward, Backward and Bi-directional LSTM-RNNs
- Mon-O-2-1-3 (2057) Subword and Crossword Units for CTC Acoustic Models
- Mon-O-2-1-4 (1430) Neural Error Corrective Language Models for Automatic Speech Recognition
- Mon-O-2-1-5 (62) Entity-Aware Language Model as an Unsupervised Reranker
- Mon-O-2-1-6 (1727) Character-level Language Modeling with Gated Hierarchical Recurrent Neural Networks

- Mon-O-2-2-1 (2443) Acoustic-Prosodic Indicators of Deception and Trust in Interview Dialogues
- Mon-O-2-2-2 (2269) Deep Personality Recognition for Deception Detection
- Mon-O-2-2-3 (1373) Cross-cultural (A)symmetries in Audio-visual Attitude Perception
- Mon-O-2-2-4 (1222) An Active Feature Transformation Method for Attitude Recognition of Video Bloggers
- Mon-O-2-2-5 (1523) Automatic Assessment of Individual Culture Attribute of Power Distance Using a Social Context-Enhanced Prosodic Network Representation
- Mon-O-2-2-6 (2502) Analysis and Detection of Phonation Modes in Singing Voice using Excitation Source Features and Single Frequency Filtering Cepstral Coefficients (SFFCC)

- Mon-O-2-3-1 (1351) A Deep Learning Method for Pathological Voice Detection Using Convolutional Deep Belief Networks
- Mon-O-2-3-2 (1754) Dysarthric Speech Recognition Using Time-delay Neural Network Based Denoising Autoencoder
- Mon-O-2-3-3 (1988) A Multitask Learning Approach to Assess the Dysarthria Severity in Patients with Parkinson's Disease
- Mon-O-2-3-4 (2398) The Use of Machine Learning and Phonetic Endophenotypes to Discover Genetic Variants Associated with Speech Sound Disorder
- Mon-O-2-3-5 (2391) Whistle-blowing ASRs: Evaluating the Need for More Inclusive Speech Recognition Systems
- Mon-O-2-3-6 (1751) Data Augmentation Using Healthy Speech for Dysarthric Speech Recognition

- Mon-O-2-4-1 (1272) Improving Sparse Representations in Exemplar-Based Voice Conversion with a Phoneme-Selective Objective Function
- Mon-O-2-4-2 (1295) Learning Structured Dictionaries for Exemplar-based Voice Conversion
- Mon-O-2-4-3 (1662) Exemplar-Based Spectral Detail Compensation for Voice Conversion
- Mon-O-2-4-4 (1487) Whispered Speech to Neutral Speech Conversion Using Bidirectional LSTMs
- Mon-O-2-4-5 (1504) Voice Conversion across Arbitrary Speakers Based on a Single Target-Speaker Utterance
- Mon-O-2-4-6 (1830) Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations

- Mon-SS-2-1-1 (-) Self-assessed Affect Sub-Challenge
- Mon-SS-2-1-2 (1610) Attention-based Sequence Classification for Affect Detection
- Mon-SS-2-1-3 (2019) Computational Paralinguistics: Automatic Assessment of Emotions, Mood and Behavioural State from Acoustics of Speech
- Mon-SS-2-1-4 (2149) Investigating Utterance Level Representations for Detecting Intent from Acoustics
- Mon-SS-2-1-5 (2298) LSTM Based Cross-corpus and Cross-task Acoustic Emotion Recognition
- Mon-SS-2-1-6 (2360) Implementing Fusion Techniques for the Classification of Paralinguistic Information
- Mon-SS-2-1-7 (1076) General Utterance-Level Feature Extraction for Classifying Crying Sounds, Atypical & Self-Assessed Affect and Heart Beats
- Mon-SS-2-1-8 (2261) Self-Assessed Affect Recognition Using Fusion of Attentional BLSTM and Static Acoustic Features
- Mon-SS-2-1-9 (1331) Vocalic, Lexical and Prosodic Cues for the INTERSPEECH 2018 Self-Assessed Affect Challenge
- Mon-SS-2-1-10 (-) The INTERSPEECH 2018 Computational Paralinguistics Challenge: Summary of result

- Mon-S&T-2-1-1 (3008) Intonation tutor by SPIRE (In-SPIRE): An online tool for an automatic feedback to the second language learners in learning intonation
- Mon-S&T-2-1-2 (3045) Game-based spoken dialog language learning applications for young students
- Mon-S&T-2-1-3 (3011) The IBM Virtual Voice Creator
- Mon-S&T-2-1-4 (3012) Mobile Application for Learning Languages for the Unlettered
- Mon-S&T-2-1-5 (3014) Mandarin-English Code-switching Speech Recognition

- Mon-P-2-1-1 (1581) Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates
- Mon-P-2-1-2 (2084) Analyzing Vocal Tract Movements During Speech Accommodation
- Mon-P-2-1-3 (1039) Cross-Lingual Multi-Task Neural Architecture for Spoken Language Understanding
- Mon-P-2-1-4 (1333) Statistical Model Compression for Small-Footprint Natural Language Understanding
- Mon-P-2-1-5 (1679) Comparison of an End-to-end Trainable Dialogue System with a Modular Statistical Dialogue System
- Mon-P-2-1-6 (1419) A Discriminative Acoustic-Prosodic Approach for Measuring Local Entrainment
- Mon-P-2-1-7 (2124) Investigating Speech Features for Continuous Turn-Taking Prediction Using LSTMs
- Mon-P-2-1-8 (1348) Classification of Correction Turns in Multilingual Dialogue Corpus
- Mon-P-2-1-9 (1035) Contextual Slot Carryover for Disparate Schemas
- Mon-P-2-1-10 (1013) Capsule Networks for Low Resource Spoken Language Understanding
- Mon-P-2-1-11 (2436) Intent Discovery through Unsupervised Semantic Text Clustering
- Mon-P-2-1-12 (2011) Multimodal Polynomial Fusion for Detecting Driver Distraction
- Mon-P-2-1-13 (2067) Engagement Recognition in Spoken Dialogue via Neural Network by Aggregating Different Annotators' Models
- Mon-P-2-1-14 (1254) A First Investigation of the Timing of Turn-taking in Ruuli

- Mon-P-2-2-1 (1042) Spoofing Detection Using Adaptive Weighting Framework and Clustering Analysis
- Mon-P-2-2-2 (1297) Exploration of Compressed ILPR Features for Replay Attack Detection
- Mon-P-2-2-3 (1473) Detection of Replay-Spoofing Attacks Using Frequency Modulation Features
- Mon-P-2-2-4 (1675) Effectiveness of Speech Demodulation-Based Features for Replay Detection
- Mon-P-2-2-5 (1687) Novel Variable Length Energy Separation Algorithm Using Instantaneous Amplitude Features for Replay Detection
- Mon-P-2-2-6 (1693) Feature with Complementarity of Statistics and Principal Information for Spoofing Detection
- Mon-P-2-2-7 (2001) Multiple Phase Information Combination for Replay Attacks Detection
- Mon-P-2-2-8 (1574) Frequency Domain Linear Prediction Features for Replay Spoofing Attack Detection
- Mon-P-2-2-9 (1651) Auditory Filterbank Learning for Temporal Modulation Features in Replay Spoof Speech Detection
- Mon-P-2-2-10 (1819) Deep Siamese Architecture Based Replay Detection for Secure Voice Biometric
- Mon-P-2-2-11 (1909) A Deep Identity Representation for Noise Robust Spoofing Detection
- Mon-P-2-2-12 (2279) End-To-End Audio Replay Attack Detection Using Deep Convolutional Networks with Attention
- Mon-P-2-2-13 (1494) Decision-level Feature Switching as a Paradigm for Replay Attack Detection
- Mon-P-2-2-14 (1846) Modulation Dynamic Features for the Detection of Replay Attacks

- Mon-P-2-3-1 (1062) On the Usefulness of the Speech Phase Spectrum for Pitch Extraction
- Mon-P-2-3-2 (1230) Time-regularized Linear Prediction for Noise-robust Extraction of the Spectral Envelope of Speech
- Mon-P-2-3-3 (1536) Auditory Filterbank Learning Using ConvRBM for Infant Cry Classification
- Mon-P-2-3-4 (1538) Effectiveness of Dynamic Features in INCA and Temporal Context-INCA
- Mon-P-2-3-5 (1224) Singing Voice Phoneme Segmentation by Hierarchically Inferring Syllable and Phoneme Onset Positions
- Mon-P-2-3-6 (1661) Novel Empirical Mode Decomposition Cepstral Features for Replay Spoof Detection
- Mon-P-2-3-7 (1702) Novel Linear Frequency Residual Cepstral Features for Replay Attack Detection
- Mon-P-2-3-8 (1921) Analysis of Sparse Representation Based Feature on Speech Mode Classification
- Mon-P-2-3-9 (1937) Multicomponent 2-D AM-FM Modeling of Speech Spectrograms
- Mon-P-2-3-10 (1987) An Optimization Framework for Recovery of Speech from Phase-Encoded Spectrograms
- Mon-P-2-3-11 (2430) Speaker Recognition with Nonlinear Distortion: Clipping Analysis and Impact
- Mon-P-2-3-12 (1128) Linear Prediction Residual Based Short-term Cepstral Features for Replay Attacks Detection
- Mon-P-2-3-13 (1947) Analysis of Variational Mode Functions for Robust Detection of Vowels

- Mon-P-2-4-1 (1030) Improving Attention Based Sequence-to-Sequence Models for End-to-End English Conversational Speech Recognition
- Mon-P-2-4-2 (1212) Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition
- Mon-P-2-4-3 (1049) Acoustic Modeling with DFSMN-CTC and Joint CTC-CE Learning
- Mon-P-2-4-4 (1888) End-to-End Speech Command Recognition with Capsule Network
- Mon-P-2-4-5 (2414) End-to-End Speech Recognition from the Raw Waveform
- Mon-P-2-4-6 (1452) A Multistage Training Framework for Acoustic-to-Word Model
- Mon-P-2-4-7 (1107) Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
- Mon-P-2-4-8 (1486) Densely Connected Networks for Conversational Speech Recognition
- Mon-P-2-4-9 (1655) Multi-Head Decoder for End-to-End Speech Recognition
- Mon-P-2-4-10 (1543) Compressing End-to-end ASR Networks by Tensor-Train Decomposition
- Mon-P-2-4-11 (2341) Speech2Vec: a Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
- Mon-P-2-4-12 (1086) Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin

- Mon-P-2-5-1 (1135) Joint Noise and Reverberation Adaptive Learning for Robust Speaker DOA Estimation with an Acoustic Vector Sensor
- Mon-P-2-5-2 (1248) Multiple Concurrent Sound Source Tracking Based on Observation-Guided Adaptive Particle Filter
- Mon-P-2-5-3 (1310) Harmonic-Percussive Source Separation of Polyphonic Music by Suppressing Impulsive Noise Events
- Mon-P-2-5-4 (1606) Speaker Activity Detection and Minimum Variance Beamforming for Source Separation
- Mon-P-2-5-5 (1615) Sparsity-Constrained Weight Mapping for Head-Related Transfer Functions Individualization from Anthropometric Features
- Mon-P-2-5-6 (1732) Speech Source Separation Using ICA in Constant Q Transform Domain
- Mon-P-2-5-7 (1739) Multi-talker Speech Separation Based on Permutation Invariant Training and Beamforming
- Mon-P-2-5-8 (1840) Expectation-Maximization Algorithms for Itakura-Saito Nonnegative Matrix Factorization
- Mon-P-2-5-9 (2173) Subband Weighting for Binaural Speech Source Localization

- Tue-O-1-1-1 (1244) Learning to Adapt: a Meta-learning Approach for Speaker Adaptation
- Tue-O-1-1-2 (2432) Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems
- Tue-O-1-1-3 (2022) Comparison of BLSTM-Layer-Specific Affine Transformations for Speaker Adaptation
- Tue-O-1-1-4 (1612) Correlational Networks for Speaker Normalization in Automatic Speech Recognition
- Tue-O-1-1-5 (1558) Machine Speech Chain with One-shot Speaker Adaptation
- Tue-O-1-1-6 (2246) Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition

- Tue-O-1-2-1 (1154) Waveform-Based Speaker Representations for Speech Synthesis
- Tue-O-1-2-2 (1561) Incremental TTS for Japanese Language
- Tue-O-1-2-3 (1265) Transfer Learning Based Progressive Neural Networks for Acoustic Modeling in Statistical Parametric Speech Synthesis
- Tue-O-1-2-4 (1590) A Unified Framework for the Generation of Glottal Signals in Deep Learning-based Parametric Speech Synthesis Systems
- Tue-O-1-2-5 (1598) Acoustic Modeling Using Adversarially Trained Variational Recurrent Neural Network for Speech Synthesis
- Tue-O-1-2-6 (1970) On the Application and Compression of Deep Time Delay Neural Network for Embedded Statistical Parametric Speech Synthesis

- Tue-O-1-3-1 (1377) Integrating Recurrence Dynamics for Speech Emotion Recognition
- Tue-O-1-3-2 (1858) Towards Temporal Modelling of Categorical Speech Emotion Recognition
- Tue-O-1-3-3 (1132) Emotion Recognition from Human Speech Using Temporal Information and Deep Learning
- Tue-O-1-3-4 (2508) Role of Regularization in the Prediction of Valence from Speech
- Tue-O-1-3-5 (1872) Learning Spontaneity to Improve Emotion Recognition in Speech
- Tue-O-1-3-6 (2464) Predicting Categorical Emotions by Jointly Learning Primary and Secondary Emotions through Multitask Learning

- Tue-O-1-4-1 (1760) Picture Naming or Word Reading: Does the Modality Affect Speech Motor Adaptation and Its Transfer?
- Tue-O-1-4-2 (1825) Measuring the Band Importance Function for Mandarin Chinese with an Bayesian Adaptive Procedure
- Tue-O-1-4-3 (2420) Wide Learning for Auditory Comprehension
- Tue-O-1-4-4 (1728) Analyzing Reaction Time Sequences from Human Participants in Auditory Experiments
- Tue-O-1-4-5 (1374) Prediction of Perceived Speech Quality Using Deep Machine Listening
- Tue-O-1-4-6 (1375) Prediction of Subjective Listening Effort from Acoustic Data with Non-Intrusive Deep Models

- Tue-O-1-5-1 (1293) A Case Study on the Importance of Belief State Representation for Dialogue Policy Management
- Tue-O-1-5-2 (1442) Prediction of Turn-taking Using Multitask Learning with Prediction of Backchannels and Fillers
- Tue-O-1-5-3 (2527) Conversational Analysis Using Utterance-level Attention-based Bidirectional Recurrent Neural Networks
- Tue-O-1-5-4 (2005) A Comparative Study of Statistical Conversion of Face to Voice Based on Their Subjective Impressions
- Tue-O-1-5-5 (1007) Follow-up Question Generation Using Pattern-based Seq2Seq with a Small Corpus for Interview Coaching
- Tue-O-1-5-6 (2446) Coherence Models for Dialogue

- Tue-SS-1-1-1 (-) Introduction
- Tue-SS-1-1-2 (2529) Indian languages ASR: A multilingual phone recognition framework with IPA based common phone-set, predicted articulatory features and feature fusion
- Tue-SS-1-1-3 (1139) Rapid Collection of Spontaneous Speech Corpora Using Telephonic Community Forums
- Tue-SS-1-1-4 (1555) Effect of TTS Generated Audio on OOV Detection and Word Error Rate in ASR for Low-resource Languages
- Tue-SS-1-1-5 (2133) Development of Large Vocabulary Speech Recognition System with Keyword Search for Manipuri
- Tue-SS-1-1-6 (2125) Robust Mizo Continuous Speech Recognition
- Tue-SS-1-1-7 (2486) Semi-supervised and Active-learning Scenarios: Efficient Acoustic Model Refinement for a Low Resource Indian Language
- Tue-SS-1-1-8 (2122) Automatic Speech Recognition with Articulatory Information and a Unified Dictionary for Hindi, Marathi, Bengali, and Oriya
- Tue-SS-1-1-9 (-) All papers in this special session
- Tue-SS-1-1-10 (-) Discussion/Q&A

- Tue-S&T-1-1-1 (3015) Captaina: Integrated pronunciation practice and data collection portal
- Tue-S&T-1-1-2 (3016) auMina - Enterprise Speech Analytics
- Tue-S&T-1-1-3 (3017) HoloCompanion: An MR Friend for EveryOne
- Tue-S&T-1-1-4 (3018) akeira - Virtual Assistant
- Tue-S&T-1-1-5 (3019) Brain-Computer Interface using Electroencephalogram signatures of Eye Blinks

- Tue-P-1-1-1 (61) Voice Comparison and Rhythm: Behavioral Differences between Target and Non-target Comparisons
- Tue-P-1-1-2 (1246) Co-whitening of I-vectors for Short and Long Duration Speaker Verification
- Tue-P-1-1-3 (1446) Compensation for Domain Mismatch in Text-independent Speaker Recognition
- Tue-P-1-1-4 (1500) Joint Learning of J-Vector Extractor and Joint Bayesian Model for Text Dependent Speaker Verification
- Tue-P-1-1-5 (1422) Latent Factor Analysis of Deep Bottleneck Features for Speaker Verification with Random Digit Strings
- Tue-P-1-1-6 (1929) VoxCeleb2: Deep Speaker Recognition
- Tue-P-1-1-7 (2012) Supervised I-vector Modeling - Theory and Applications
- Tue-P-1-1-8 (2412) LOCUST - Longitudinal Corpus and Toolset for Speaker Verification
- Tue-P-1-1-9 (2071) Analysis of Language Dependent Front-End for Speaker Recognition - Tue-P-1-1-10 (2221) Robust Speaker Recognition from Distant Speech under Real Reverberant Environments Using Speaker Embeddings
- Tue-P-1-1-11 (2394) Investigation on Bandwidth Extension for Speaker Recognition
- Tue-P-1-1-12 (1696) On Learning Vocal Tract System Related Speaker Discriminative Information from Raw Signal Using CNNs
- Tue-P-1-1-13 (1759) On Convolutional LSTM Modeling for Joint Wake-Word Detection and Text Dependent Speaker Verification
- Tue-P-1-1-14 (1593) Cosine Metric Learning for Speaker Verification in the I-vector Space
- Tue-P-1-1-15 (1363) An Unsupervised Neural Prediction Framework for Learning Speaker Embeddings Using Recurrent Neural Networks

- Tue-P-1-2-1 (1223) A New Framework for Supervised Speech Enhancement in the Time Domain
- Tue-P-1-2-2 (1294) Speech Enhancement Using the Minimum-probability-of-error Criterion
- Tue-P-1-2-3 (1387) Exploring the Relationship between Conic Affinity of NMF Dictionaries and Speech Enhancement Metrics
- Tue-P-1-2-4 (1650) Using Shifted Real Spectrum Mask as Training Target for Supervised Speech Separation
- Tue-P-1-2-5 (1928) Enhancement of Noisy Speech Signal by Non-Local Means Estimation of Variational Mode Functions
- Tue-P-1-2-6 (1950) Phase-locked Loop Based Phase Estimation in Single Channel Speech Enhancement
- Tue-P-1-2-7 (2409) Cycle-Consistent Speech Enhancement
- Tue-P-1-2-8 (1955) Visual Speech Enhancement
- Tue-P-1-2-9 (2031) Implementation of Digital Hearing Aid as a Smartphone Application
- Tue-P-1-2-10 (1046) Bone-Conduction Sensor Assisted Noise Estimation for Improved Speech Enhancement
- Tue-P-1-2-11 (2213) Artificial Bandwidth Extension with Memory Inclusion Using Semi-supervised Stacked Auto-encoders
- Tue-P-1-2-12 (2383) Large Vocabulary Concatenative Resynthesis
- Tue-P-1-2-13 (2439) Concatenative Resynthesis with Improved Training Signals for Speech Enhancement

- Tue-P-1-3-1 (1047) Comparison of Syllabification Algorithms and Training Strategies for Robust Word Count Estimation across Different Languages and Recording Conditions
- Tue-P-1-3-2 (1115) A Comparison of Input Types to a Deep Neural Network-based Forced Aligner
- Tue-P-1-3-3 (1151) Joint Learning Using Denoising Variational Autoencoders for Voice Activity Detection
- Tue-P-1-3-4 (1203) Information Bottleneck Based Percussion Instrument Diarization System for Taniavartanam Segments of Carnatic Music Concerts
- Tue-P-1-3-5 (1431) Robust Voice Activity Detection Using Frequency Domain Long-Term Differential Entropy
- Tue-P-1-3-6 (1531) Device-directed Utterance Detection
- Tue-P-1-3-7 (1692) Acoustic-Prosodic Features of Tabla Bol Recitation and Correspondence with the Tabla Imitation
- Tue-P-1-3-8 (1807) Who Said That? a Comparative Study of Non-negative Matrix Factorization Techniques
- Tue-P-1-3-9 (2028) AVA-Speech: a Densely Labeled Dataset of Speech Activity in Movies
- Tue-P-1-3-10 (2490) Audiovisual Speech Activity Detection with Advanced Long Short-Term Memory
- Tue-P-1-3-11 (2537) Towards Automatic Speech Identification from Vocal Tract Shape Dynamics in Real-time MRI

- Tue-P-1-4-1 (1057) Structured Word Embedding for Low Memory Neural Network Language Model
- Tue-P-1-4-2 (2185) Role Play Dialogue Aware Language Models Based on Conditional Hierarchical Recurrent Encoder-Decoder
- Tue-P-1-4-3 (1979) Efficient Keyword Spotting Using Time Delay Neural Networks
- Tue-P-1-4-4 (2062) Automatic DNN Node Pruning Using Mixture Distribution-based Group Regularization
- Tue-P-1-4-5 (2195) Conditional Computation-Based Recurrent Neural Networks for Computationally Efficient Acoustic Modelling
- Tue-P-1-4-6 (2162) Leveraging Translations for Speech Transcription in Low-resource Settings
- Tue-P-1-4-7 (1381) Sequence-to-sequence Neural Network Model with 2D Attention for Learning Japanese Pitch Accents
- Tue-P-1-4-8 (2211) Task Specific Sentence Embeddings for ASR Error Detection
- Tue-P-1-4-9 (1055) Low-Latency Neural Speech Translation
- Tue-P-1-4-10 (1326) Low-Resource Speech-to-Text Translation
- Tue-P-1-4-11 (2032) VoiceGuard: Secure and Private Speech Processing

- Tue-O-2-1-1 (1234) Single-channel Speech Dereverberation via Generative Adversarial Training
- Tue-O-2-1-2 (1296) Single-Channel Dereverberation Using Direct MMSE Optimization and Bidirectional LSTM Networks
- Tue-O-2-1-3 (1660) Single-channel Late Reverberation Power Spectral Density Estimation Using Denoising Autoencoders
- Tue-O-2-1-4 (1834) A Non-convolutive NMF Model for Speech Dereverberation
- Tue-O-2-1-5 (2238) Cross-Corpora Convolutional Deep Neural Network Dereverberation Preprocessing for Speaker Verification and Speech Enhancement
- Tue-O-2-1-6 (2306) Dereverberation and Beamforming in Robust Far-Field Speaker Recognition

- Tue-O-2-2-1 (990) Comparing the Max and Noisy-Or Pooling Functions in Multiple Instance Learning for Weakly Supervised Sequence Learning Tasks
- Tue-O-2-2-2 (2338) A Simple Model for Detection of Rare Sound Events
- Tue-O-2-2-3 (1152) Temporal Transformer Networks for Acoustic Scene Classification
- Tue-O-2-2-4 (1552) Temporal Attentive Pooling for Acoustic Event Detection
- Tue-O-2-2-5 (2323) R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection
- Tue-O-2-2-6 (2559) Detecting Media Sound Presence in Acoustic Scenes

- Tue-O-2-3-1 (1232) S4D: Speaker Diarization Toolkit in Python
- Tue-O-2-3-2 (1364) Multimodal Speaker Segmentation and Diarization Using Lexical and Acoustic Cues via Sequence to Sequence Neural Networks
- Tue-O-2-3-3 (1654) Combined Speaker Clustering and Role Recognition in Conversational Speech
- Tue-O-2-3-4 (2324) The ACLEW DiViMe: an Easy-to-use Diarization Tool
- Tue-O-2-3-5 (1878) Automatic Detection of Multi-speaker Fragments with High Time Resolution
- Tue-O-2-3-6 (1750) Neural Speech Turn Segmentation and Affinity Propagation for Speaker Diarization

- Tue-O-2-4-1 (1638) Pitch or Phonation: on the Glottalization in Tone Productions in the Ruokeng Hui Chinese Dialect
- Tue-O-2-4-2 (2288) Speaker-specific Structure in German Voiceless Stop Voice Onset Times
- Tue-O-2-4-3 (2165) Creak in the Respiratory Cycle
- Tue-O-2-4-4 (2598) Acoustic Analysis of Whispery Voice Disguise in Mandarin Chinese
- Tue-O-2-4-5 (1542) The Zurich Corpus of Vowel and Voice Quality, Version 1.0
- Tue-O-2-4-6 (1677) Weighting of Coda Voicing Cues: Glottalisation and Vowel Duration

- Tue-O-2-5-1 (1908) Revealing Spatiotemporal Brain Dynamics of Speech Production Based on EEG and Eye Movement
- Tue-O-2-5-2 (2072) Neural Response Development During Distributional Learning
- Tue-O-2-5-3 (2130) Learning Two Tone Languages Enhances the Brainstem Encoding of Lexical Tones
- Tue-O-2-5-4 (2505) Perceptual Sensitivity to Spectral Change in Australian English Close Front Vowels: an Electroencephalographic Investigation
- Tue-O-2-5-5 (1024) Effective Acoustic Cue Learning Is Not Just Statistical, It Is Discriminative
- Tue-O-2-5-6 (1676) Analyzing EEG Signals in Auditory Speech Comprehension Using Temporal Response Functions and Generalized Additive Models

- Tue-SS-2-1-1 (1896) Information Encoding by Deep Neural Networks: What Can We Learn?
- Tue-SS-2-1-2 (1034) Scalable Factorized Hierarchical Variational Autoencoder Training
- Tue-SS-2-1-3 (1153) State Gradients for RNN Memory Analysis
- Tue-SS-2-1-4 (2462) Exploring How Phone Classification Neural Networks Learn Phonetic Information by Visualising and Interpreting Bottleneck Features
- Tue-SS-2-1-5 (2082) Memory Time Span in LSTMs for Multi-Speaker Source Separation
- Tue-SS-2-1-6 (1707) Visualizing Phoneme Category Adaptation in Deep Neural Networks

- Tue-S&T-2-1-1 (3022) Early vocabulary development through picture-based software solutions
- Tue-S&T-2-1-2 (3026) Automatic detection of expressiveness in oral reading
- Tue-S&T-2-1-3 (3027) PannoMulloKathan: Voice enabled Mobile App for Agricultural Commodity Price Dissemination in Bengali Language
- Tue-S&T-2-1-4 (3028) Visualizing Punctuation Restoration in Speech Transcripts with Prosograph
- Tue-S&T-2-1-5 (3029) CACTAS - Collaborative Audio Categorization and Transcription for ASR Systems

- Tue-P-2-1-1 (2087) FACTS: a Hierarchical Task-based Control Model of Speech Incorporating Sensory Feedback
- Tue-P-2-1-2 (2592) Sensorimotor response to tongue displacement imagery by talkers with Parkinson’s disease
- Tue-P-2-1-3 (1267) Automatic Pronunciation Evaluation of Singing
- Tue-P-2-1-4 (2299) Classification of Nonverbal Human Produced Audio Events: a Pilot Study
- Tue-P-2-1-5 (995) UltraFit: a Speaker-friendly Headset for Ultrasound Recordings in Speech Sciences
- Tue-P-2-1-6 (1038) Articulatory Consequences of Vocal Effort Elicitation Method
- Tue-P-2-1-7 (1233) Age-related Effects on Sensorimotor Control of Speech Production
- Tue-P-2-1-8 (2512) An Ultrasound Study of Gemination in Coronal Stops in Eastern Oromo
- Tue-P-2-1-9 (1646) Processing Transition Regions of Glottal Stop Substituted /S/ for Intelligibility Enhancement of Cleft Palate Speech
- Tue-P-2-1-10 (1907) Reconstructing Neutral Speech from Tracheoesophageal Speech
- Tue-P-2-1-11 (2544) Automatic Evaluation of Soft Articulatory Contact for Stuttering Treatment
- Tue-P-2-1-12 (1575) Korean Singing Voice Synthesis Based on LSTM Recurrent Neural Network
- Tue-P-2-1-13 (60) The Trajectory of Voice Onset Time with Vocal Aging

- Tue-P-2-2-1 (1768) The Fifth `CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines
- Tue-P-2-2-2 (1454) Voices Obscured in Complex Environmental Settings (VOiCES) Corpus
- Tue-P-2-2-3 (1262) Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline
- Tue-P-2-2-4 (1097) Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition
- Tue-P-2-2-5 (1780) Investigating Generative Adversarial Networks Based Speech Dereverberation for Robust Speech Recognition
- Tue-P-2-2-6 (1547) Monaural Multi-Talker Speech Recognition with Attention Mechanism and Gated Convolutional Networks
- Tue-P-2-2-7 (1721) Weighting Time-Frequency Representation of Speech Using Auditory Saliency for Automatic Speech Recognition
- Tue-P-2-2-8 (1453) Acoustic Modeling from Frequency Domain Representations of Speech
- Tue-P-2-2-9 (1828) Non-Uniform Spectral Smoothing for Robust Children's Speech Recognition
- Tue-P-2-2-10 (1134) Bidirectional Long-Short Term Memory Network-based Estimation of Reliable Spectral Component Locations
- Tue-P-2-2-11 (2156) Speech Emotion Recognition by Combining Amplitude and Phase Information Using Convolutional Neural Network
- Tue-P-2-2-12 (2377) Bubble Cooperative Networks for Identifying Important Speech Cues

- Tue-P-2-3-1 (34) Real-Time Scoring of an Oral Reading Assessment on Mobile Devices
- Tue-P-2-3-2 (1087) A Deep Learning Approach to Assessing Non-native Pronunciation of English Using Phone Distances
- Tue-P-2-3-3 (1270) Paired Phone-Posteriors Approach to ESL Pronunciation Quality Assessment
- Tue-P-2-3-4 (1350) Investigating the Role of L1 in Automatic Pronunciation Evaluation of L2 Speech
- Tue-P-2-3-5 (1312) Impact of ASR Performance on Free Speaking Language Assessment
- Tue-P-2-3-6 (1644) Automatic Miscue Detection Using RNN Based Models with Data Augmentation
- Tue-P-2-3-7 (1860) A Study of Objective Measurement of Comprehensibility through Native Speakers' Shadowing of Learners' Utterances
- Tue-P-2-3-8 (2138) Factorized Deep Neural Network Adaptation for Automatic Scoring of L2 Speech in English Speaking Tests
- Tue-P-2-3-9 (2297) On the Difficulties of Automatic Speech Recognition for Kindergarten-Aged Children
- Tue-P-2-3-10 (2118) Improved Acoustic Modelling for Automatic Literacy Assessment of Children

- Tue-SS-2-2-1 (1319) Anomaly Detection Approach for Pronunciation Verification of Disordered Speech Using Speech Attribute Features
- Tue-SS-2-2-2 (1399) Effectiveness of Voice Quality Features in Detecting Depression
- Tue-SS-2-2-3 (1465) Fusing Text-dependent Word-level i-Vector Models to Screen ‘at Risk’ Child Speech
- Tue-SS-2-2-4 (1471) Testing Paradigms for Assistive Hearing Devices in Diverse Acoustic Environments
- Tue-SS-2-2-5 (1514) Detection of Dementia from Responses to Atypical Questions Asked by Embodied Conversational Agents
- Tue-SS-2-2-6 (1521) Acoustic Features Associated with Sustained Vowel and Continuous Speech Productions by Chinese Children with Functional Articulation Disorders
- Tue-SS-2-2-7 (1631) Estimation of Hypernasality Scores from Cleft Lip and Palate Speech
- Tue-SS-2-2-8 (1713) Detecting Alzheimer’s Disease Using Gated Convolutional Neural Network from Audio Data
- Tue-SS-2-2-9 (2475) Automatic Detection of Orofacial Impairment in Stroke
- Tue-SS-2-2-10 (2522) Detecting Depression with Audio/Text Sequence Modeling of Interviews

- Tue-P-2-5-1 (2129) Discourse Marker Detection for Hesitation Events on Mandarin Conversation
- Tue-P-2-5-2 (2225) Acoustic and Perceptual Characteristics of Mandarin Speech in Homosexual and Heterosexual Male Speakers
- Tue-P-2-5-3 (1755) Automatic Question Detection from Acoustic and Phonetic Features Using Feature-wise Pre-training
- Tue-P-2-5-4 (2310) Improving Response Time of Active Speaker Detection Using Visual Prosody Information Prior to Articulation
- Tue-P-2-5-5 (2215) Audio-Visual Prediction of Head-Nod and Turn-Taking Events in Dyadic Interactions
- Tue-P-2-5-6 (1425) Analyzing Effect of Physical Expression on English Proficiency for Multimodal Computer-Assisted Language Learning
- Tue-P-2-5-7 (2090) Analysis of the Effect of Speech-Laugh on Speaker Recognition System
- Tue-P-2-5-8 (2418) Vocal Biomarkers for Cognitive Performance Estimation in a Working Memory Task
- Tue-P-2-5-9 (2263) Lexical and Acoustic Deep Learning Model for Personality Recognition

- Wed-O-1-1-1 (1485) Layer Trajectory LSTM
- Wed-O-1-1-2 (2158) Semi-tied Units for Efficient Gating in LSTM and Highway Networks
- Wed-O-1-1-3 (1823) Gaussian Process Neural Networks for Speech Recognition
- Wed-O-1-1-4 (1089) Acoustic Modeling with Densely Connected Residual Network for Multichannel Speech Recognition
- Wed-O-1-1-5 (1544) Gated Recurrent Unit Based Acoustic Modeling with Future Context
- Wed-O-1-1-6 (1403) Output-Gate Projected Gated Recurrent Unit for Speech Recognition

- Wed-O-1-2-1 (69) Performance Analysis of the 2017 NIST Language Recognition Evaluation
- Wed-O-1-2-2 (1165) Using Deep Neural Networks for Identification of Slavic Languages from Acoustic Signal
- Wed-O-1-2-3 (1342) Adding New Classes without Access to the Original Training Data with Applications to Language Identification
- Wed-O-1-2-4 (1519) Feature Representation of Short Utterances Based on Knowledge Distillation for Spoken Language Identification
- Wed-O-1-2-5 (1805) Sub-band Envelope Features Using Frequency Domain Linear Prediction for Short Duration Language Identification
- Wed-O-1-2-6 (2458) Effectiveness of Single-Channel BLSTM Enhancement for Language Identification

- Wed-O-1-3-1 (1384) Articulation Rate as a Speaker Discriminant in British English
- Wed-O-1-3-2 (2513) Truncation and Compression in Southern German and Australian English
- Wed-O-1-3-3 (1873) Prominence-based Evaluation of L2 Prosody
- Wed-O-1-3-4 (1060) Length Contrast and Covarying Features: Whistled Speech as a Case Study
- Wed-O-1-3-5 (1529) Information Structure, Affect, and Prenuclear Prominence in American English
- Wed-O-1-3-6 (63) Effects of User Controlled Speech Rate on Intelligibility in Noisy Environments

- Wed-O-1-4-1 (27) Binaural Speech Intelligibility Estimation Using Deep Neural Networks
- Wed-O-1-4-2 (1291) Multi-resolution Gammachirp Envelope Distortion Index for Intelligibility Prediction of Noisy Speech
- Wed-O-1-4-3 (2119) Speech Intelligibility Enhancement Based on a Non-causal Wavenet-like Model
- Wed-O-1-4-4 (1802) Quality-Net: an End-to-End Non-intrusive Speech Quality Assessment Model Based on BLSTM
- Wed-O-1-4-5 (1884) Global Snr Estimation of Speech Signals Using Entropy and Uncertainty Estimates from Dropout Networks
- Wed-O-1-4-6 (1098) Detecting Packet-Loss Concealment Using Formant Features and Decision Tree Learning

- Wed-SS-1-1-1 (1736) UltraSuite: a Repository of Ultrasound and Acoustic Data from Child Speech Therapy Sessions
- Wed-SS-1-1-2 (1764) Detecting Signs of Dementia Using Word Vector Representations
- Wed-SS-1-1-3 (2029) Classification of Huntington Disease Using Acoustic and Lexical Features
- Wed-SS-1-1-4 (2355) The PRIORI Emotion Dataset: Linking Mood to Emotion Detected In-the-Wild
- Wed-SS-1-1-5 (1518) Language Features for Automated Evaluation of Cognitive Behavior Psychotherapy Sessions
- Wed-SS-1-1-6 (2496) Automatic Early Detection of Amyotrophic Lateral Sclerosis from Intelligible Speech Using Convolutional Neural Networks

- Wed-SS-1-2-1 (1600) A Study of Lexical and Prosodic Cues to Segmentation in a Hindi-English Code-switched Discourse
- Wed-SS-1-2-2 (1966) Building a Unified Code-Switching ASR System for South African Languages
- Wed-SS-1-2-3 (1974) Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition
- Wed-SS-1-2-4 (52) Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech
- Wed-SS-1-2-5 (1099) The Role of Cognate Words, POS Tags, and Entrainment in Code-Switching
- Wed-SS-1-2-6 (1171) Homophone Identification and Merging for Code-switched Speech Recognition
- Wed-SS-1-2-7 (1178) Code-switching in Indic Speech Synthesisers
- Wed-SS-1-2-8 (1259) A Novel Approach for Effective Recognition of the Code-Switched Data on Monolingual Language Model

- Wed-S&T-1-1-1 (3030) Hierarchical Accent Determination and Application in a Large Scale ASR System
- Wed-S&T-1-1-2 (3032) Toward Scalable Dialog Technology for Conversational Language Learning: Case Study of the TOEFL MOOC
- Wed-S&T-1-1-3 (3033) Machine Learning powered Data Platform for High-Quality Speech and NLP workflows
- Wed-S&T-1-1-4 (3034) Fully automatic speaker separation system, with automatic enrolling of recurrent speakers
- Wed-S&T-1-1-5 (3035) Online speech translation system for Tamil

- Wed-P-1-1-1 (1712) Unsupervised Vocal Tract Length Warped Posterior Features for Non-Parallel Voice Conversion
- Wed-P-1-1-2 (1121) Voice Conversion with Conditional SampleRNN
- Wed-P-1-1-3 (1131) A Voice Conversion Framework with Tandem Feature Sparse Representation and Speaker-Adapted WaveNet Vocoder
- Wed-P-1-1-4 (1190) WaveNet Vocoder with Limited Training Data for Voice Conversion
- Wed-P-1-1-5 (1210) Collapsed Speech Segment Detection and Suppression for WaveNet Vocoder
- Wed-P-1-1-6 (1528) High-quality Voice Conversion Using Spectrogram-Based WaveNet Vocoder
- Wed-P-1-1-7 (2417) Spanish Statistical Parametric Speech Synthesis Using a Neural Vocoder
- Wed-P-1-1-8 (2400) Experiments with Training Corpora for Statistical Text-to-speech Systems.
- Wed-P-1-1-9 (1506) Multi-task WaveNet: a Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions
- Wed-P-1-1-10 (1635) Speaker-independent Raw Waveform Model for Glottal Excitation
- Wed-P-1-1-11 (1757) A New Glottal Neural Vocoder for Speech Synthesis
- Wed-P-1-1-12 (1857) Exemplar-based Speech Waveform Generation
- Wed-P-1-1-13 (43) Frequency Domain Variants of Velvet Noise and Their Application to Speech Processing and Synthesis

- Wed-P-1-2-1 (1346) Joint Learning of Interactive Spoken Content Retrieval and Trainable User Simulator
- Wed-P-1-2-2 (1777) Attention-based End-to-End Models for Small-Footprint Keyword Spotting
- Wed-P-1-2-3 (991) Prediction of Aesthetic Elements in Karnatic Music: a Machine Learning Approach
- Wed-P-1-2-4 (1283) Topic and Keyword Identification for Low-resourced Speech Using Cross-Language Transfer Learning
- Wed-P-1-2-5 (1836) Automatic Speech Recognition and Topic Identification from Speech for Almost-Zero-Resource Languages
- Wed-P-1-2-6 (1100) Play Duration Based User-Entity Affinity Modeling in Spoken Dialog System
- Wed-P-1-2-7 (1776) Empirical Analysis of Score Fusion Application to Combined Neural Networks for Open Vocabulary Spoken Term Detection
- Wed-P-1-2-8 (1973) Phonological Posterior Hashing for Query by Example Spoken Term Detection
- Wed-P-1-2-9 (2017) Term Extraction via Neural Sequence Labeling a Comparative Evaluation of Strategies Using Recurrent Neural Networks
- Wed-P-1-2-10 (1318) Semi-supervised Learning for Information Extraction from Dialogue
- Wed-P-1-2-11 (1808) Slot Filling with Delexicalized Sentence Generation
- Wed-P-1-2-12 (2045) Music Genre Recognition Using Deep Neural Networks and Transfer Learning
- Wed-P-1-2-13 (2204) Efficient Voice Trigger Detection for Low Resource Hardware

- Wed-P-1-3-1 (45) A Novel Normalization Method for Autocorrelation Function for Pitch Detection and for Speech Activity Detection
- Wed-P-1-3-2 (1105) Estimation of the Vocal Tract Length of Vowel Sounds Based on the Frequency of the Significant Spectral Valley
- Wed-P-1-3-3 (1143) Deep Learning Techniques for Koala Activity Detection
- Wed-P-1-3-4 (1147) Glottal Closure Instant Detection from Speech Signal Using Voting Classifier and Recursive Feature Elimination
- Wed-P-1-3-5 (1463) Assessing Speaker Engagement in 2-Person Debates: Overlap Detection in United States Presidential Debates
- Wed-P-1-3-6 (1522) All-Conv Net for Bird Activity Detection: Significance of Learned Pooling
- Wed-P-1-3-7 (1705) Deep Convex Representations: Feature Representations for Bioacoustics Classification
- Wed-P-1-3-8 (2014) Detection of Glottal Excitation Epochs in Speech Signal Using Hilbert Envelope
- Wed-P-1-3-9 (2115) Analyzing Thai Tone Distribution through Functional Data Analysis
- Wed-P-1-3-10 (2275) Articulatory Feature Classification Using Convolutional Neural Networks
- Wed-P-1-3-11 (2590) A New Frequency Coverage Metric and a New Subband Encoding Model, with an Application in Pitch Estimation
- Wed-P-1-3-12 (1173) Improved Epoch Extraction from Telephonic Speech Using Chebfun and Zero Frequency Filtering

- Wed-P-1-4-1 (2530) An Empirical Analysis of the Correlation of Syntax and Prosody
- Wed-P-1-4-2 (2533) Analysing the Focus of a Hierarchical Attention Network: the Importance of Enjambments When Classifying Post-modern Poetry
- Wed-P-1-4-3 (1962) Language-Dependent Melody Embeddings
- Wed-P-1-4-4 (1602) Stress Distribution of Given Information in Chinese Reading Texts
- Wed-P-1-4-5 (2366) Acoustic-prosodic Entrainment in Structural Metadata Events
- Wed-P-1-4-6 (1126) Formant Measures of Vowels Adjacent to Alveolar and Retroflex Consonants in Arrernte: Stressed and Unstressed Position
- Wed-P-1-4-7 (1386) Automatic Assessment of L2 English Word Prosody Using Weighted Distances of F0 and Intensity Contours
- Wed-P-1-4-8 (1476) Homogeneity vs Heterogeneity in Indian English: Investigating Influences of L1 on f0 Range
- Wed-P-1-4-9 (91) Emotional Prosody Perception in Mandarin-speaking Congenital Amusics
- Wed-P-1-4-10 (1795) Cultural Differences in Pattern Matching: Multisensory Recognition of Socio-affective Prosody

- Wed-O-2-1-1 (1456) ESPnet: End-to-End Speech Processing Toolkit
- Wed-O-2-1-2 (1339) A GPU-based WFST Decoder with Exact Lattice Generation
- Wed-O-2-1-3 (1085) Automatic Speech Recognition System Development in the "Wild"
- Wed-O-2-1-4 (2453) Semantic Lattice Processing in Contextual Automatic Speech Recognition for Google Assistant
- Wed-O-2-1-5 (2416) Contextual Speech Recognition in End-to-end Neural Network Systems Using Beam Search
- Wed-O-2-1-6 (1160) Forward-Backward Attention Decoder

- Wed-O-2-2-1 (1015) Learning Discriminative Features for Speaker Identification and Verification
- Wed-O-2-2-2 (1209) Triplet Loss Based Cosine Similarity Metric Learning for Text-independent Speaker Recognition
- Wed-O-2-2-3 (1226) Speaker Embedding Extraction with Phonetic Information
- Wed-O-2-2-4 (993) Attentive Statistics Pooling for Deep Speaker Embedding
- Wed-O-2-2-5 (1685) Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization
- Wed-O-2-2-6 (1769) Deep Discriminative Embeddings for Duration Robust Speaker Verification

- Wed-O-2-3-1 (1358) Impact of Different Speech Types on Listening Effort
- Wed-O-2-3-2 (2053) Who Are You Listening to? towards a Dynamic Measure of Auditory Attention to Speech-on-speech.
- Wed-O-2-3-3 (1812) Investigating the Role of Familiar Face and Voice Cues in Speech Processing in Noise
- Wed-O-2-3-4 (1088) The Conversation Continues: the Effect of Lyrics and Music Complexity of Background Music on Spoken-Word Recognition
- Wed-O-2-3-5 (2089) Loud and Shouted Speech Perception at Variable Distances in a Forest
- Wed-O-2-3-6 (1271) Phoneme Resistance and Phoneme Confusion in Noise: Impact of Dyslexia

- Wed-O-2-4-1 (38) Conditional End-to-End Audio Transforms
- Wed-O-2-4-2 (1018) Detection of Glottal Closure Instants in Degraded Speech Using Single Frequency Filtering Analysis
- Wed-O-2-4-3 (2293) Tone Recognition Using Lifters and CTC
- Wed-O-2-4-4 (1613) Epoch Extraction from Pathological Children Speech Using Single Pole Filtering Approach
- Wed-O-2-4-5 (1756) Automated Classification of Vowel-Gesture Parameters Using External Broadband Excitation
- Wed-O-2-4-6 (2495) Estimation of Fundamental Frequency from Singing Voice Using Harmonics of Impulse-like Excitation Source

- Wed-O-2-5-1 (57) Investigating the Effect of Audio Duration on Dementia Detection Using Acoustic Features
- Wed-O-2-5-2 (1288) An Interlocutor-Modulated Attentional LSTM for Differentiating between Subgroups of Autism Spectrum Disorder
- Wed-O-2-5-3 (1772) Recognition of Echolalic Autistic Child Vocalisations Utilising Convolutional Recurrent Neural Networks
- Wed-O-2-5-4 (1562) Modeling Interpersonal Influence of Verbal Behavior in Couples Therapy Dyadic Interactions
- Wed-O-2-5-5 (1583) Computational Modeling of Conversational Humor in Psychotherapy
- Wed-O-2-5-6 (2295) Multimodal I-vectors to Detect and Evaluate Parkinson's Disease

- Wed-SS-2-1-1 (97) Overview of the 2018 Spoken CALL Shared Task
- Wed-SS-2-1-2 (1000) The CSU-K Rule-Based System for the 2Nd Edition Spoken CALL Shared Task
- Wed-SS-2-1-3 (1309) Liulishuo's System for the Spoken CALL Shared Task 2018
- Wed-SS-2-1-4 (1328) An Optimization Based Approach for Solving Spoken CALL Shared Task
- Wed-SS-2-1-5 (1372) The University of Birmingham 2018 Spoken CALL Shared Task Systems
- Wed-SS-2-1-6 (2362) Improvements to an Automated Content Scoring System for Spoken CALL Responses: the ETS Submission to the Second Spoken CALL Shared Task
- Wed-SS-2-1-7 (-) Closing Remarks and General Discussion

- Wed-S&T-2-1-1 (3036) Extracting speaker’s gender, accent, age and emotional state from speech
- Wed-S&T-2-1-2 (3042) Determining Speaker Location from Speech in a Practical Environment
- Wed-S&T-2-1-3 (3043) An Automatic Speech Transcription System for Manipuri Language
- Wed-S&T-2-1-4 (3009) SPIRE-SST: An automatic web-based self-learning tool for syllable stress tutoring (SST) to the second language learners
- Wed-S&T-2-1-5 (3046) Glotto Vibrato Graph: A Device and Method for Recording, Analysis and Visualization of Glottal Activity

- Wed-P-2-1-1 (2456) Multi-Modal Data Augmentation for End-to-end ASR
- Wed-P-2-1-2 (1866) Multi-task Learning with Augmentation Strategy for Acoustic-to-word Attention-based Encoder-decoder Speech Recognition
- Wed-P-2-1-3 (1247) Training Augmentation with Adversarial Examples for Robust Speech Recognition
- Wed-P-2-1-4 (1211) Data Augmentation Improves Recognition of Foreign Accented Speech
- Wed-P-2-1-5 (2209) Speaker Adaptive Training and Mixup Regularization for Neural Network Acoustic Models in Automatic Speech Recognition
- Wed-P-2-1-6 (1241) Neural Language Codes for Multilingual Acoustic Models
- Wed-P-2-1-7 (1424) Encoder Transfer for Attention-based Acoustic-to-word Speech Recognition
- Wed-P-2-1-8 (1897) Empirical Evaluation of Speaker Adaptation on DNN Based Acoustic Model
- Wed-P-2-1-9 (1450) Improving DNNs Trained with Non-Native Transcriptions Using Knowledge Distillation and Target Interpolation
- Wed-P-2-1-10 (1182) Improving Cross-Lingual Knowledge Transferability Using Multilingual TDNN-BLSTM with Language-Dependent Pre-Final Layer
- Wed-P-2-1-11 (1438) Auxiliary Feature Based Adaptation of End-to-end ASR Systems
- Wed-P-2-1-12 (1378) Leveraging Native Language Information for Improved Accented Speech Recognition
- Wed-P-2-1-13 (1864) Improved Accented Speech Recognition Using Accent Embeddings and Multi-task Learning
- Wed-P-2-1-14 (1990) Fast Language Adaptation Using Phonological Information

- Wed-P-2-2-1 (1239) Naturalness Improvement Algorithm for Reconstructed Glossectomy Patient's Speech Using Spectral Differential Modification in Voice Conversion
- Wed-P-2-2-2 (2286) Audio-visual Voice Conversion Using Deep Canonical Correlation Analysis for Deep Bottleneck Features
- Wed-P-2-2-3 (1869) An Investigation of Convolution Attention Based Models for Multilingual Speech Synthesis of Indian Languages
- Wed-P-2-2-4 (2066) The Effect of Real-Time Constraints on Automatic Speech Animation
- Wed-P-2-2-5 (2587) Joint Learning of Facial Expression and Head Pose from Speech
- Wed-P-2-2-6 (1306) Acoustic-dependent Phonemic Transcription for Text-to-speech Synthesis
- Wed-P-2-2-7 (1791) Multimodal Speech Synthesis Architecture for Unsupervised Speaker Adaptation
- Wed-P-2-2-8 (999) Articulatory-to-speech Conversion Using Bi-directional Long Short-term Memory
- Wed-P-2-2-9 (1080) Implementation of Respiration in Articulatory Synthesis Using a Pressure-Volume Lung Model
- Wed-P-2-2-10 (1198) Learning and Modeling Unit Embeddings for Improving HMM-based Unit Selection Speech Synthesis
- Wed-P-2-2-11 (1305) Deep Metric Learning for the Target Cost in Unit-Selection Speech Synthesizer
- Wed-P-2-2-12 (1460) DNN-based Speech Synthesis for Small Data Sets Considering Bidirectional Speech-Text Conversion
- Wed-P-2-2-13 (1286) A Weighted Superposition of Functional Contours Model for Modelling Contextual Prominence of Elementary Prosodic Contours
- Wed-P-2-2-14 (1753) LSTBM: a Novel Sequence Representation of Speech Spectra Using Restricted Boltzmann Machine with Long Short-Term Memory

- Wed-P-2-3-1 (1284) Should Code-switching Models Be Asymmetric?
- Wed-P-2-3-2 (48) Cross-language Perception of Mandarin Lexical Tones by Mongolian-speaking Bilinguals in the Inner Mongolia Autonomous Region, China
- Wed-P-2-3-3 (1336) Automatically Measuring L2 Speech Fluency without the Need of ASR: a Proof-of-concept Study with Japanese Learners of French
- Wed-P-2-3-4 (1983) Analysis of L2 Learners’ Progress of Distinguishing Mandarin Tone 2 and Tone 3
- Wed-P-2-3-5 (2027) Unsupervised Discovery of Non-native Phonetic Patterns in L2 English Speech for Mispronunciation Detection and Diagnosis
- Wed-P-2-3-6 (2224) Wuxi Speakers’ Production and Perception of Coda Nasals in Mandarin
- Wed-P-2-3-7 (2373) The Diphthongs of Formal Nigerian English: a Preliminary Acoustic Analysis
- Wed-P-2-3-8 (1798) Characterizing Rhythm Differences between Strong and Weak Accented L2 Speech
- Wed-P-2-3-9 (2422) Analysis of phone errors attributable to phonological effects associated with language acquisition through bottleneck feature visualisations
- Wed-P-2-3-10 (1938) Category Similarity in Multilingual Pronunciation Training
- Wed-P-2-3-11 (2078) Talker Diarization in the Wild: the Case of Child-centered Daylong Audio-recordings
- Wed-P-2-3-12 (2523) Automated Classification of Children’S Linguistic versus Non-Linguistic Vocalisations
- Wed-P-2-3-13 (1556) Pitch Characteristics of L2 English Speech by Chinese Speakers: a Large-scale Study

- Wed-P-2-4-1 (1343) Dual Language Models for Code Switched Speech Recognition
- Wed-P-2-4-2 (1711) Multilingual Neural Network Acoustic Modelling for ASR of Under-Resourced English-isiZulu Code-Switched Speech
- Wed-P-2-4-3 (1580) Fast ASR-free and Almost Zero-resource Keyword Spotting Using DTW and CNNs for Humanitarian Monitoring
- Wed-P-2-4-4 (1668) Text-Dependent Speech Enhancement for Small-Footprint Robust Keyword Detection
- Wed-P-2-4-5 (1124) Improved ASR for Under-resourced Languages through Multi-task Learning with Acoustic Landmarks
- Wed-P-2-4-6 (2454) Cross-language Phoneme Mapping for Low-resource Languages: an Exploration of Benefits and Trade-offs
- Wed-P-2-4-7 (1352) User-centric Evaluation of Automatic Punctuation in ASR Closed Captioning
- Wed-P-2-4-8 (1096) Punctuation Prediction Model for Conversational Speech
- Wed-P-2-4-9 (2457) BUT OpenSAT 2017 Speech Recognition System
- Wed-P-2-4-10 (2434) Visual Recognition of Continuous Cued Speech Using a Tandem CNN-HMM Approach
- Wed-P-2-4-11 (2112) Building Large-vocabulary Speaker-independent Lipreading Systems
- Wed-P-2-4-12 (2079) CRIM's System for the MGB-3 English Multi-Genre Broadcast Media Transcription
- Wed-P-2-4-13 (2384) Sampling Strategies in Siamese Networks for Unsupervised Speech Representation Learning
- Wed-P-2-4-14 (1204) Compact Feedforward Sequential Memory Networks for Small-footprint Keyword Spotting

- Wed-O-3-1-1 (2334) Multilingual Bottleneck Features for Subword Modeling in Zero-resource Languages
- Wed-O-3-1-2 (1081) Exploiting Speaker and Phonetic Diversity of Mismatched Language Resources for Unsupervised Subword Modeling
- Wed-O-3-1-3 (1308) Unsupervised Word Segmentation from Speech with Attention
- Wed-O-3-1-4 (2364) Learning Word Embeddings: Unsupervised Methods for Fixed-size Representations of Variable-length Speech Segments
- Wed-O-3-1-5 (2148) Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery
- Wed-O-3-1-6 (2194) Unspeech: Unsupervised Speech Context Embeddings

- Wed-O-3-2-1 (1371) Impact of Aliasing on Deep CNN-Based End-to-End Acoustic Models
- Wed-O-3-2-2 (1526) Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment
- Wed-O-3-2-3 (1629) End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction
- Wed-O-3-2-4 (1773) PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation
- Wed-O-3-2-5 (1940) Integrating Spectral and Spatial Features for Multi-Channel Speaker Separation
- Wed-O-3-2-6 (2516) DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation

- Wed-O-3-3-1 (1256) Exploring Temporal Reduction in Dialectal Spanish: a Large-scale Study of Lenition of Voiced Stops and Coda-s
- Wed-O-3-3-2 (1130) Dialect-geographical Acoustic-Tonetics: Five Disyllabic Tone Sandhi Patterns in Cognate Words from the Wu Dialects of ZhèJiāNg Province
- Wed-O-3-3-3 (1065) Regional Variation of /r/ in Swiss German Dialects
- Wed-O-3-3-4 (1944) Variation in the FACE Vowel across West Yorkshire: Implications for Forensic Speaker Comparisons
- Wed-O-3-3-5 (65) The ‘West Yorkshire Regional English Database’: Investigations into the Generalizability of Reference Populations for Forensic Speaker Comparison Casework
- Wed-O-3-3-6 (2381) Studying Vowel Variation in French-Algerian Arabic Code-switched Speech

- Wed-O-3-4-1 (1942) Fearless Steps: Apollo-11 Corpus Advancements for Speech Technologies from Earth to the Moon
- Wed-O-3-4-2 (1516) A Knowledge Driven Structural Segmentation Approach for Play-Talk Classification During Autism Assessment
- Wed-O-3-4-3 (1349) An Open Source Emotional Speech Corpus for Human Robot Interaction Applications
- Wed-O-3-4-4 (2330) Speech Database and Protocol Validation Using Waveform Entropy
- Wed-O-3-4-5 (2212) A French-Spanish Multimodal Speech Communication Corpus Incorporating Acoustic Data, Facial, Hands and Arms Gestures Information
- Wed-O-3-4-6 (1110) L2-ARCTIC: a Non-native English Speech Corpus

- Wed-SS-3-1-1 (1252) ZCU-NTIS Speaker Diarization System for the DIHARD 2018 Challenge
- Wed-SS-3-1-2 (1742) Speaker Diarization with Enhancing Speech for the First DIHARD Challenge
- Wed-SS-3-1-3 (1749) BUT System for DIHARD Speech Diarization Challenge 2018
- Wed-SS-3-1-4 (1841) Estimation of the Number of Speakers with Variational Bayesian PLDA in the DIHARD Diarization Challenge.
- Wed-SS-3-1-5 (1893) Diarization Is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge
- Wed-SS-3-1-6 (2172) The EURECOM Submission to the First DIHARD Challenge
- Wed-SS-3-1-7 (2304) Joint Discriminative Embedding Learning, Speech Activity and Overlap Detection for the DIHARD Speaker Diarization Challenge

- Wed-P-3-1-1 (1626) Multilingual Grapheme-to-Phoneme Conversion with Global Character Vectors
- Wed-P-3-1-2 (1694) A Hybrid Approach to Grapheme to Phoneme Conversion in Assamese
- Wed-P-3-1-3 (2525) Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion
- Wed-P-3-1-4 (1174) Using Pupillometry to Measure the Cognitive Load of Synthetic Speech
- Wed-P-3-1-5 (1199) Measuring the Cognitive Load of Synthetic Speech Using a Dual Task Paradigm
- Wed-P-3-1-6 (42) Attentive Sequence-to-Sequence Learning for Diacritic Restoration of YorùBá Language Text
- Wed-P-3-1-7 (70) Gated Convolutional Neural Network for Sentence Matching
- Wed-P-3-1-8 (1920) On Training and Evaluation of Grapheme-to-Phoneme Mappings with Limited Data
- Wed-P-3-1-9 (1093) The Perception and Analysis of the Likeability and Human Likeness of Synthesized Speech
- Wed-P-3-1-10 (1159) Word Emphasis Prediction for Expressive Text to Speech
- Wed-P-3-1-11 (1313) A Comparison of Speaker-based and Utterance-based Data Selection for Text-to-Speech Synthesis
- Wed-P-3-1-12 (1316) Data Requirements, Selection and Augmentation for DNN-based Speech Synthesis from Crowdsourced Data

- Wed-P-3-2-1 (2361) Lightly Supervised vs. Semi-supervised Training of Acoustic Model on Luxembourgish for Low-resource Automatic Speech Recognition
- Wed-P-3-2-2 (1597) Investigation on the Combination of Batch Normalization and Dropout in BLSTM-based Acoustic Modeling for ASR
- Wed-P-3-2-3 (1563) Inference-Invariant Transformation of Batch Normalization for Domain Adaptation of Acoustic Models
- Wed-P-3-2-4 (1162) Active Learning for LF-MMI Trained Neural Networks in ASR
- Wed-P-3-2-5 (2191) An Investigation of Mixup Training Strategies for Acoustic Models in ASR
- Wed-P-3-2-6 (1972) Comparison of Unsupervised Modulation Filter Learning Methods for ASR
- Wed-P-3-2-7 (2517) Improved Training for Online End-to-end Speech Recognition Systems
- Wed-P-3-2-8 (2335) Combining Natural Gradient with Hessian Free Methods for Sequence Training
- Wed-P-3-2-9 (79) Lattice-free State-level Minimum Bayes Risk Training of Acoustic Models
- Wed-P-3-2-10 (2030) A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition
- Wed-P-3-2-11 (1891) Multilingual Deep Neural Network Training Using Cyclical Learning Rate

- Wed-P-3-3-1 (1541) Development of the CUHK Dysarthric Speech Recognition System for the UA Speech Corpus
- Wed-P-3-3-2 (1266) Automatic Evaluation of Speech Intelligibility Based on I-vectors in the Context of Head and Neck Cancers
- Wed-P-3-3-3 (2250) Dysarthric Speech Recognition Using Convolutional LSTM Neural Network
- Wed-P-3-3-4 (1264) Perceptual and Automatic Evaluations of the Intelligibility of Speech Degraded by Noise Induced Hearing Loss Simulation
- Wed-P-3-3-5 (67) Articulatory Features for ASR of Pathological Speech
- Wed-P-3-3-6 (1806) Mining Multimodal Repositories for Speech Affecting Diseases
- Wed-P-3-3-7 (1428) Long Distance Voice Channel Diagnosis Using Deep Neural Networks
- Wed-P-3-3-8 (40) Speech Recognition for Medical Conversations

- Wed-P-3-4-1 (1320) Prosodic Focus Acquisition in French Early Cochlear Implanted Children
- Wed-P-3-4-2 (1725) The Role of Temporal Variation in Narrative Organization
- Wed-P-3-4-3 (1827) Interaction Mechanisms between Glottal Source and Vocal Tract in Pitch Glides
- Wed-P-3-4-4 (1862) Relating Articulatory Motions in Different Speaking Rates
- Wed-P-3-4-5 (2371) Estimation of the Asymmetry Parameter of the Glottal Flow Waveform Using the Electroglottographic Signal
- Wed-P-3-4-6 (1967) Classification of Disorders in Vocal Folds Using Electroglottographic Signal
- Wed-P-3-4-7 (2572) Automatic Glottis Localization and Segmentation in Stroboscopic Videos Using Deep Neural Network
- Wed-P-3-4-8 (1948) Respiratory and Respiratory Muscular Control in JL1’S and JL2’S Text Reading Utilizing 4-RSTs and a Soft Respiratory Mask with a Two-Way Bulb
- Wed-P-3-4-9 (1849) A Preliminary Study on Tonal Coarticulation in Continuous Speech

- Thu-O-1-1-1 (2003) Far-Field Speech Recognition Using Multivariate Autoregressive Models
- Thu-O-1-1-2 (2566) Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models
- Thu-O-1-1-3 (1037) Stream Attention for Distributed Multi-Microphone Speech Recognition
- Thu-O-1-1-4 (2284) Recognizing Overlapped Speech in Meetings: a Multichannel Separation Approach Using Neural Networks
- Thu-O-1-1-5 (2196) Integrating Neural Network Based Beamforming and Weighted Prediction Error Dereverberation
- Thu-O-1-1-6 (2427) A Probability Weighted Beamformer for Noise Robust ASR

- Thu-O-1-2-1 (2042) Effects of Dimensional Input on Paralinguistic Information Perceived from Synthesized Dialogue Speech with Neural Network
- Thu-O-1-2-2 (2174) Neural MultiVoice Models for Expressing Novel Personalities in Dialog
- Thu-O-1-2-3 (2467) Expressive Speech Synthesis Using Sentiment Embeddings
- Thu-O-1-2-4 (1113) Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
- Thu-O-1-2-5 (1991) Rapid Style Adaptation Using Residual Error Embedding for Expressive Speech Synthesis
- Thu-O-1-2-6 (1511) EMPHASIS: an Emotional Phoneme-based Acoustic Model for Speech Synthesis System

- Thu-O-1-3-1 (996) Bags in Bag: Generating Context-Aware Bags for Tracking Emotions from Speech
- Thu-O-1-3-2 (1242) An Attention Pooling Based Representation Learning Method for Speech Emotion Recognition
- Thu-O-1-3-3 (2397) Predicting Arousal and Valence from Waveforms and Spectrograms Using Deep Neural Networks
- Thu-O-1-3-4 (1353) Emotion Identification from Raw Speech Signals Using DNNs
- Thu-O-1-3-5 (1455) Encoding Individual Acoustic Features Using Dyad-Augmented Deep Variational Representations for Dialog-level Emotion Recognition
- Thu-O-1-3-6 (1568) Variational Autoencoders for Learning Latent Representations of Speech Emotion: a Preliminary Study

- Thu-O-1-4-1 (1202) Phoneme-to-Articulatory Mapping Using Bidirectional Gated RNN
- Thu-O-1-4-2 (1108) Tongue Segmentation with Geometrically Constrained Snake Model
- Thu-O-1-4-3 (1843) Low Resource Acoustic-to-articulatory Inversion Using Bi-directional Long Short Term Memory
- Thu-O-1-4-4 (1570) Automatic Visual Augmentation for Concatenation Based Synthesized Articulatory Videos from Real-time MRI Data for Spoken Language Training
- Thu-O-1-4-5 (1939) Air-Tissue Boundary Segmentation in Real-Time Magnetic Resonance Imaging Video Using Semantic Segmentation with Fully Convolutional Networks
- Thu-O-1-4-6 (1509) Noise Robust Acoustic to Articulatory Speech Inversion

- Thu-SS-1-1-1 (-) Welcome and Introduction
- Thu-SS-1-1-2 (1043) Designing a Pneumatic Bionic Voice Prosthesis - A Statistical Approach for Source Excitation Generation
- Thu-SS-1-1-3 (1904) A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation
- Thu-SS-1-1-4 (2484) Articulation-to-Speech Synthesis Using Articulatory Flesh Point Sensors’ Orientation Information
- Thu-SS-1-1-5 (1565) Effectiveness of Generative Adversarial Network for Non-Audible Murmur-to-Whisper Speech Conversion
- Thu-SS-1-1-6 (2080) Investigating Objective Intelligibility in Real-Time EMG-to-Speech Conversion
- Thu-SS-1-1-7 (2318) Domain-Adversarial Training for Session Independent EMG-based Speech Recognition
- Thu-SS-1-1-8 (1078) Multi-Task Learning of Speech Recognition and Speech Synthesis Parameters for Ultrasound-based Silent Speech Interfaces
- Thu-SS-1-1-9 (-) Discussion and Closing

- Thu-SS-1-2-1 (-) Introduction
- Thu-SS-1-2-2 (1188) Transcription Correction for Indian Languages Using Acoustic Signatures
- Thu-SS-1-2-3 (1302) BUT System for Low Resource Indian Language ASR
- Thu-SS-1-2-4 (1553) DA-IICT/IIITV System for Low Resource Speech Recognition Challenge 2018
- Thu-SS-1-2-5 (1584) An Exploration towards Joint Acoustic Modeling for Indian Languages: IIIT-H Submission for Low Resource Speech Recognition Challenge for Indian Languages, INTERSPEECH 2018
- Thu-SS-1-2-6 (2117) TDNN-based Multilingual Speech Recognition System for Low Resource Indian Languages
- Thu-SS-1-2-7 (2226) Articulatory and Stacked Bottleneck Features for Low Resource Speech Recognition
- Thu-SS-1-2-8 (2473) ISI ASR System for the Low Resource Speech Recognition Challenge for Indian Languages

- Thu-S&T-1-1-1 (3047) An automated assistant for medical scribes
- Thu-S&T-1-1-2 (3048) AGROASSAM: A Web Based Assamese Speech Recognition Application for Retrieving Agricultural Commodity Price and Weather Information
- Thu-S&T-1-1-3 (3049) Voice-powered solutions with Cloud AI
- Thu-S&T-1-1-4 (3050) Speech synthesis in the wild

- Thu-P-1-1-1 (1020) Deep Noise Tracking Network: a Hybrid Signal Processing/Deep Learning Approach to Speech Enhancement
- Thu-P-1-1-2 (1114) A Deep Neural Network Based Harmonic Noise Model for Speech Enhancement
- Thu-P-1-1-3 (1405) A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement
- Thu-P-1-1-4 (1664) All-Neural Multi-Channel Speech Enhancement
- Thu-P-1-1-5 (1484) Deep Learning for Acoustic Echo Cancellation in Noisy and Double-Talk Scenarios
- Thu-P-1-1-6 (1400) The Conversation: Deep Audio-Visual Speech Enhancement
- Thu-P-1-1-7 (2440) Student-Teacher Learning for BLSTM Mask-based Speech Enhancement
- Thu-P-1-1-8 (1730) Speech Enhancement Using Deep Mixture of Experts Based on Hard Expectation Maximization
- Thu-P-1-1-9 (2461) Adversarial Feature-Mapping for Speech Enhancement
- Thu-P-1-1-10 (1237) Biophysically-inspired Features Improve the Generalizability of Neural Network-based Speech Enhancement Systems
- Thu-P-1-1-11 (1439) Error Modeling via Asymmetric Laplace Distribution for Deep Neural Network Based Single-Channel Speech Enhancement
- Thu-P-1-1-12 (2423) A Priori SNR Estimation Based on a Recurrent Neural Network for Robust Speech Enhancement

- Thu-P-1-2-1 (1120) Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection
- Thu-P-1-2-2 (1243) Unsupervised Temporal Feature Learning Based on Sparse Coding Embedded BoAW for Acoustic Event Recognition
- Thu-P-1-2-3 (1250) Data Independent Sequence Augmentation Method for Acoustic Scene Classification
- Thu-P-1-2-4 (1299) A Compact and Discriminative Feature Based on Auditory Summary Statistics for Acoustic Scene Classification
- Thu-P-1-2-5 (1481) ASe: Acoustic Scene Embedding Using Deep Archetypal Analysis and GMM
- Thu-P-1-2-6 (1524) Deep Convolutional Neural Network with Scalogram for Audio Scene Modeling
- Thu-P-1-2-7 (1637) Time Aggregation Operators for Multi-label Audio Event Detection
- Thu-P-1-2-8 (1821) Early Detection of Continuous and Partial Audio Events Using CNN
- Thu-P-1-2-9 (1905) Robust Acoustic Event Classification Using Bag-of-Visual-Words
- Thu-P-1-2-10 (2083) Wavelet Transform Based Mel-scaled Features for Acoustic Scene Classification
- Thu-P-1-2-11 (1138) Multi-modal Attention Mechanisms in LSTM and Its Application to Acoustic Scene Classification

- Thu-P-1-3-1 (1122) Contextual Language Model Adaptation for Conversational Agents
- Thu-P-1-3-2 (78) Active Memory Networks for Language Modeling
- Thu-P-1-3-3 (1021) Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR
- Thu-P-1-3-4 (1111) Improving Language Modeling with an Adversarial Critic for Automatic Speech Recognition
- Thu-P-1-3-5 (1369) Training Recurrent Neural Network through Moment Matching for NLP Applications
- Thu-P-1-3-6 (2476) Investigation on LSTM Recurrent N-gram Language Models for Speech Recognition
- Thu-P-1-3-7 (2259) Online Incremental Learning for Speaker-Adaptive Language Models
- Thu-P-1-3-8 (1345) Efficient Language Model Adaptation with Noise Contrastive Estimation and Kullback-Leibler Regularization
- Thu-P-1-3-9 (1413) Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition
- Thu-P-1-3-10 (84) What to Expect from Expected Kneser-Ney Smoothing
- Thu-P-1-3-11 (1070) i-Vectors in Language Modeling: an Efficient Way of Domain Adaptation for Feed-Forward Models

- Thu-P-1-4-1 (2040) How Did You like 2017? Detection of Language Markers of Depression and Narcissism in Personal Narratives
- Thu-P-1-4-2 (1743) Depression Detection from Short Utterances via Diverse Smartphones in Natural Environmental Conditions
- Thu-P-1-4-3 (2169) Multi-Lingual Depression-Level Assessment from Conversational Speech Using Acoustic and Text Features
- Thu-P-1-4-4 (1059) Dysarthric Speech Classification Using Glottal Features Computed from Non-words, Words and Sentences
- Thu-P-1-4-5 (1079) Identifying Schizophrenia Based on Temporal Parameters in Spontaneous Speech
- Thu-P-1-4-6 (2551) Using Prosodic and Lexical Information for Learning Utterance-level Behaviors in Psychotherapy
- Thu-P-1-4-7 (1630) Automatic Speech Assessment for People with Aphasia Using TDNN-BLSTM with Multi-Task Learning
- Thu-P-1-4-8 (1395) Towards an Unsupervised Entrainment Distance in Conversational Speech Using Deep Neural Networks
- Thu-P-1-4-9 (2186) Patient Privacy in Paralinguistic Tasks
- Thu-P-1-4-10 (2155) A Lightly Supervised Approach to Detect Stuttering in Children's Speech
- Thu-P-1-4-11 (1298) Learning Conditional Acoustic Latent Representation with Gender and Age Attributes for Automatic Pain Level Recognition

- Thu-O-2-1-1 (1379) A Deep Reinforcement Learning Based Multimodal Coaching Model (DCM) for Slot Filling in Spoken Language Understanding(SLU)
- Thu-O-2-1-2 (2256) Is ATIS Too Shallow to Go Deeper for Benchmarking Spoken Language Understanding Models?
- Thu-O-2-1-3 (2358) Robust Spoken Language Understanding via Paraphrasing
- Thu-O-2-1-4 (1714) Spoken SQuAD: a Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
- Thu-O-2-1-5 (1149) User Information Augmented Semantic Frame Parsing Using Progressive Neural Networks
- Thu-O-2-1-6 (2403) An Efficient Approach to Encoding Context for Spoken Language Understanding

- Thu-O-2-2-1 (83) Deep Speech Denoising with Vector Space Projections
- Thu-O-2-2-2 (1150) A Shifted Delta Coefficient Objective for Monaural Speech Separation Using Multi-task Learning
- Thu-O-2-2-3 (1406) A Two-Stage Approach to Noisy Cochannel Speech Separation with Gated Residual Networks
- Thu-O-2-2-4 (1140) Monoaural Audio Source Separation Using Variational Autoencoders
- Thu-O-2-2-5 (2065) Towards Automated Single Channel Source Separation Using Neural Networks
- Thu-O-2-2-6 (2441) Investigations on Data Augmentation and Loss Functions for Deep Learning Based Speech-Background Separation

- Thu-O-2-3-1 (1019) Annotator Trustability-based Cooperative Learning Solutions for Intelligent Audio Analysis
- Thu-O-2-3-2 (1063) Semi-supervised Cross-domain Visual Feature Learning for Audio-Visual Broadcast Speech Transcription
- Thu-O-2-3-3 (1943) Deep Lip Reading: a Comparison of Models and an Online Application
- Thu-O-2-3-4 (1447) Iterative Learning of Speech Recognition Models for Air Traffic Control
- Thu-O-2-3-5 (2359) Speaker Adaptive Audio-Visual Fusion for the Open-Vocabulary Section of AVICAR
- Thu-O-2-3-6 (1748) Multimodal Name Recognition in Live TV Subtitling

- Thu-O-2-4-1 (46) Dithered Quantization for Frequency-Domain Speech and Audio Coding
- Thu-O-2-4-2 (1026) Postfiltering with Complex Spectral Correlations for Speech and Audio Coding
- Thu-O-2-4-3 (1027) Postfiltering Using Log-Magnitude Spectrum for Speech and Audio Coding
- Thu-O-2-4-4 (2096) Temporal Noise Shaping with Companding
- Thu-O-2-4-5 (2577) Multi-frame Quantization of LSF Parameters Using a Deep Autoencoder and Pyramid Vector Quantizer
- Thu-O-2-4-6 (2578) Multi-frame Coding of LSF Parameters Using Block-Constrained Trellis Coded Vector Quantization

- Thu-P-2-1-1 (1044) Training Utterance-level Embedding Networks for Speaker Identification and Verification
- Thu-P-2-1-2 (1102) Analysis of Complementary Information Sources in the Speaker Embeddings Framework
- Thu-P-2-1-3 (1158) Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
- Thu-P-2-1-4 (1515) An Improved Deep Embedding Learning Method for Short Duration Speaker Verification
- Thu-P-2-1-5 (1608) Avoiding Speaker Overfitting in End-to-End DNNs Using Raw Waveform for Text-Independent Speaker Verification
- Thu-P-2-1-6 (1688) Deeply Fused Speaker Embeddings for Text-Independent Speaker Verification
- Thu-P-2-1-7 (1804) Employing Phonetic Information in DNN Speaker Embeddings to Improve Speaker Recognition Performance
- Thu-P-2-1-8 (2300) End-to-end Text-dependent Speaker Verification Using Novel Distance Measures
- Thu-P-2-1-9 (50) Robust Speaker Clustering using Mixtures of von Mises-Fisher Distributions for Naturalistic Audio Streams
- Thu-P-2-1-10 (2305) Triplet Network with Attention for Speaker Diarization
- Thu-P-2-1-11 (1680) I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification
- Thu-P-2-1-12 (92) Analysis of Length Normalization in End-to-End Speaker Verification System
- Thu-P-2-1-13 (1545) Angular Softmax for Short-Duration Text-independent Speaker Verification
- Thu-P-2-1-14 (1058) An End-to-End Text-Independent Speaker Identification System on Short Utterances
- Thu-P-2-1-15 (1023) MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks

- Thu-P-2-2-1 (47) Categorical vs Dimensional Perception of Italian Emotional Speech
- Thu-P-2-2-2 (1820) A Three-Layer Emotion Perception Model for Valence and Arousal-Based Detection from Multilingual Speech
- Thu-P-2-2-3 (1778) Cross-lingual Speech Emotion Recognition through Factor Analysis
- Thu-P-2-2-4 (2222) Modeling Self-Reported and Observed Affect from Speech
- Thu-P-2-2-5 (1327) Stochastic Shake-Shake Regularization for Affective Learning from Speech
- Thu-P-2-2-6 (2350) Investigating Speech Enhancement and Perceptual Quality for Speech Emotion Recognition
- Thu-P-2-2-7 (1933) Demonstrating and Modelling Systematic Time-varying Annotator Disagreement in Continuous Emotion Annotation
- Thu-P-2-2-8 (1432) Speech Emotion Recognition from Variable-Length Inputs with Triplet Loss Function
- Thu-P-2-2-9 (1744) Imbalance Learning-based Framework for Fear Recognition in the MediaEval Emotional Impact of Movies Task
- Thu-P-2-2-10 (2228) Emotion Recognition from Variable-Length Speech Segments Using Deep Learning on Spectrograms
- Thu-P-2-2-11 (1811) Speech Emotion Recognition Using Spectrogram & Phoneme Embedding
- Thu-P-2-2-12 (1883) On Enhancing Speech Emotion Recognition Using Generative Adversarial Networks
- Thu-P-2-2-13 (1391) Ladder Networks for Emotion Recognition: Using Unsupervised Auxiliary Tasks to Improve Predictions of Emotional Attributes

- Thu-P-2-3-1 (1589) Knowledge Distillation for Sequence Model
- Thu-P-2-3-2 (1475) Improving CTC-based Acoustic Model with Very Deep Residual Time-delay Neural Networks
- Thu-P-2-3-3 (1370) Filter Sampling and Combination CNN (FSC-CNN): a Compact CNN Model for Small-footprint ASR Acoustic Modeling Using Raw Waveforms
- Thu-P-2-3-4 (1407) Twin Regularization for Online Speech Recognition
- Thu-P-2-3-5 (1910) Self-Attentional Acoustic Models
- Thu-P-2-3-6 (1797) Hierarchical Recurrent Neural Networks for Acoustic Modeling
- Thu-P-2-3-7 (2061) Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme Prediction
- Thu-P-2-3-8 (1156) Leveraging Second-Order Log-Linear Model for Improved Deep Learning Based ASR Performance
- Thu-P-2-3-9 (1417) Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks
- Thu-P-2-3-10 (1800) Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings
- Thu-P-2-3-11 (1376) Phone Recognition Using a Non-Linear Manifold with Broad Phone Class Dependent DNNs
- Thu-P-2-3-12 (1535) A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation

- Thu-P-2-4-1 (2025) Interactions between Vowels and Nasal Codas in Mandarin Speakers’ Perception of Nasal Finals
- Thu-P-2-4-2 (1245) Weighting Pitch Contour and Loudness Contour in Mandarin Tone Perception in Cochlear Implant Listeners
- Thu-P-2-4-3 (2081) Implementing DIANA to Model Isolated Auditory Word Recognition in English
- Thu-P-2-4-4 (2114) Effects of Homophone Density on Spoken Word Recognition in Mandarin Chinese
- Thu-P-2-4-5 (1285) Visual Timing Information in Audiovisual Speech Perception: Evidence from Lexical Tone Contour
- Thu-P-2-4-6 (73) COSMO SylPhon: A Bayesian perceptuo-motor model to assess phonological learning
- Thu-P-2-4-7 (2104) Experience-dependent Influence of Music and Language on Lexical Pitch Learning Is Not Additive
- Thu-P-2-4-8 (2331) Influences of Fundamental Oscillation on Speaker Identification in Vocalic Utterances by Humans and Computers