Interspeech 2019

948 papers

Top Research Directions

Research directions most represented by Interspeech 2019 papers.

Partitioning Variance with Linear Mixed Effects Models 33
Feature Learning Directly from Raw Audio Waveforms 21
The Single Speaker Generalization Bottleneck in Speech Synthesis 21
Learning Fixed Length Representations of Vocal Identity 19
Generalizing from Limited Cohorts in Speech Research 19
Robust Natural Language Understanding for Noisy Speech Transcripts 18
Speech Transformation Without Parallel Training Data 17
Mitigating Far-Field Acoustic Degradation in Speech Processing 16
Joint Optimization of Speech Enhancement and Recognition 15
Recovering Articulatory Movements from Speech Audio 14
Generalization to Unseen Acoustic Environments 14
Robust Audio Modeling Under Acoustic Domain Shift 14
Temporal Alignment of Speech and Text 13
Fine-Grained Prosodic Control for Expressive Speech Synthesis 13
Generalizing Speech Models to Unseen Acoustic Environments 13

Top Authors

AuthorPapers
Haizhou Li20
Shinji Watanabe12
Hung-yi Lee9
Najim Dehak9
Xunying Liu9
Helen M. Meng8
Jianhua Tao8
Jun Du8
Yanmin Qian8
Shrikanth Narayanan7
Dong Yu6
Yonghong Yan6
Alfonso Ortega5
Bin Liu5
EngSiong Chng5
James R. Glass5
Jiangyan Yi5
Kai Yu5
Kong Aik Lee5
Panayiotis Georgiou5

Impactful Papers

Papers from Interspeech 2019 that shaped research clusters.

Foundational

Influential

Papers

Title
Towards an Annotation Scheme for Complex Laughter in Speech Corpora
Towards a Speaker Independent Speech-BCI Using Speaker Adaptation
Towards Bilingual Lexicon Discovery From Visually Grounded Speech Audio
Towards Debugging Deep Neural Networks by Generating Speech Utterances
Towards Detection of Canonical Babbling by Citizen Scientists: Performance as a Function of Clip Length
Towards Generalized Speech Enhancement with Generative Adversarial Networks
Towards Joint Sound Scene and Polyphonic Sound Event Recognition
Towards Language-Universal Mandarin-English Speech Recognition
Towards Robust Speech Emotion Recognition Using Deep Residual Networks for Speech Enhancement
Towards the Prosody of Persuasion in Competitive Negotiation. The Relationship Between f0 and Negotiation Success in Same Sex Sales Tasks
Towards the Speech Features of Early-Stage Dementia: Design and Application of the Mandarin Elderly Cognitive Speech Database
Towards the Speech Features of Mild Cognitive Impairment: Universal Evidence from Structured and Unstructured Connected Speech of Chinese
Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues
Towards Using Context-Dependent Symbols in CTC Without State-Tying Decision Trees
Towards Variability Resistant Dialectal Speech Evaluation
Tracking the New Zealand English NEAR/SQUARE Merger Using Functional Principal Components Analysis
Trainable Dynamic Subsampling for End-to-End Speech Recognition
Training Multi-Speaker Neural Text-to-Speech Systems Using Speaker-Imbalanced Speech Corpora
Transfer Learning from Audio-Visual Grounding to Speech Recognition
Transfer-Representation Learning for Detecting Spoofing Attacks with Converted and Synthesized Speech in Automatic Speaker Verification System
Transformer Based Grapheme-to-Phoneme Conversion
Transparent Pronunciation Scoring Using Articulatorily Weighted Phoneme Edit Distance
Turn-Taking Prediction Based on Detection of Transition Relevance Place
Two-Dimensional Convolutional Recurrent Neural Networks for Speech Activity Detection
Two-Pass End-to-End Speech Recognition
Two-Stage Training for Chinese Dialect Recognition
Two Tiered Distributed Training Algorithm for Acoustic Modeling
Ultra-Compact NLU: Neuronal Network Binarization as Regularization
Ultrasound-Based Silent Speech Interface Built on a Continuous Vocoder
Ultrasound Tongue Imaging for Diarization and Alignment of Child Speech Therapy Sessions
Unbabel Talk — Human Verified Translations for Voice Instant Messaging
Unbiased Semi-Supervised LF-MMI Training Using Dropout
Understanding and Visualizing Raw Waveform-Based CNNs
UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-Noise Ratio Condition
Unidirectional Neural Network Architectures for End-to-End Automatic Speech Recognition
Unified Language-Independent DNN-Based G2P Converter
Unified Verbalization for Speech Recognition & Synthesis Across Languages
Universal Adversarial Perturbations for Speech Recognition Systems
Unleashing the Unused Potential of i-Vectors Enabled by GPU Acceleration
Unsupervised Acoustic Segmentation and Clustering Using Siamese Network Embeddings
Unsupervised Acoustic Unit Discovery for Speech Synthesis Using Discrete Latent-Variable Neural Networks
Unsupervised Adaptation with Adversarial Dropout Regularization for Robust Speech Recognition
Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
Unsupervised Low-Rank Representations for Speech Emotion Recognition
Unsupervised Methods for Audio Classification from Lecture Discussion Recordings
Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages
Unsupervised Raw Waveform Representation Learning for ASR
Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
Unsupervised Singing Voice Conversion
Unsupervised Training of Neural Mask-Based Beamforming

« prev Page 18/19 next »