Interspeech 2021

979 papers

Top Research Directions

Research directions most represented by Interspeech 2021 papers.

Partitioning Variance with Linear Mixed Effects Models 34
Integrating Local and Global Context in Speech Architectures 31
Learning High-Level Acoustic Structures from Unlabeled Audio 30
The Single Speaker Generalization Bottleneck in Speech Synthesis 27
Balancing Latency and Accuracy in Streaming Speech Recognition 26
Zero Shot Speaker Generalization for Speech Synthesis 24
Overcoming Data Scarcity in Low-Resource Speech Recognition 23
Generalization to Unseen Acoustic Environments 20
Generalizing from Limited Cohorts in Speech Research 20
The Perceptual Evaluation Gap in Generative Audio 19
Resolving Overlapping Speech in Multi-Speaker Audio 18
Conformer Architectures for Perceptual Speech Enhancement 17
Bridging the Gap Between Read and Spontaneous Speech 17
Robust Natural Language Understanding for Noisy Speech Transcripts 17
Complex Spectral Mapping for Phase Aware Signal Reconstruction 16

Top Authors

AuthorPapers
Shinji Watanabe20
Haizhou Li12
Binghuai Lin10
Jinyu Li10
Jing Xiao9
Christian Fuegen8
Jun Du8
Brian Kingsbury7
Dong Yu7
Hung-yi Lee7
Najim Dehak7
Athanasios Mouchtaris6
Helen M. Meng6
James R. Glass6
Jesus Villalba6
Jianzong Wang6
Longbiao Wang6
Naoyuki Kanda6
Peter Bell6
Piotr Zelasko6

Impactful Papers

Papers from Interspeech 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Transfer Learning and Data Augmentation Techniques to the COVID-19 Identification Tasks in ComParE 2021
Transfer Learning-Based Cough Representations for Automatic Detection of COVID-19
Transfer Learning for Speech Intelligibility Improvement in Noisy Environments
Transformer-Based Acoustic Modeling for Streaming Speech Synthesis
Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation
Transformer Based End-to-End Mispronunciation Detection and Diagnosis
Triple M: A Practical Text-to-Speech Synthesis System with Multi-Guidance Attention and Multi-Band Multi-Time LPCNet
Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments
TVQVC: Transformer Based Vector Quantized Variational Autoencoder with CTC Loss for Voice Conversion
Two-Pathway Style Embedding for Arbitrary Voice Conversion
Ultra Fast Speech Separation Model with Teacher Student Learning
Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data
Uncovering the Acoustic Cues of COVID-19 Infection
Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction
Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation
Unified Source-Filter GAN: Unified Source-Filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN
UnitNet-Based Hybrid Speech Synthesis
Universal Speaker Extraction in the Presence and Absence of Target Speakers for Speech of One and Two Talkers
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation
Unsupervised Bayesian Adaptation of PLDA for Speaker Verification
Unsupervised Cross-Lingual Representation Learning for Speech Recognition
Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization
Unsupervised Learning of Disentangled Speech Content and Style Representation
Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification
Unsupervised Neural-Based Graph Clustering for Variable-Length Speech Representation Discovery of Zero-Resource Languages
Unsupervised Representation Learning for Speech Activity Detection in the Fearless Steps Challenge 2021
Unsupervised Training of a DNN-Based Formant Tracker
User-Initiated Repetition-Based Recovery in Multi-Utterance Dialogue Systems
Using Games to Augment Corpora for Language Recognition and Confusability
Using Large Self-Supervised Models for Low-Resource Speech Recognition
Using the Outputs of Different Automatic Speech Recognition Paradigms for Acoustic- and BERT-Based Alzheimer’s Dementia Detection Through Spontaneous Speech
Using Transposed Convolution for Articulatory-to-Acoustic Conversion from Real-Time MRI Data
Using X-Vectors for Speech Activity Detection in Broadcast Streams
Utilizing Self-Supervised Representations for MOS Prediction
VAD-Free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording
VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis
Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning
Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
Variational Information Bottleneck Based Regularization for Speaker Recognition
Variational Information Bottleneck for Effective Low-Resource Audio Classification
Variation in Perceptual Sensitivity and Compensation for Coarticulation Across Adult and Child Naturally-Produced and TTS Voices
ViSTAFAE: A Visual Speech-Training Aid with Feedback of Articulatory Efforts
Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing
Visual Speech for Obstructive Sleep Apnea Detection
Visual Transformers for Primates Classification and Covid Detection
Vocal Harmony Separation Using Time-Domain Neural Networks
Vocalization Recognition of People with Profound Intellectual and Multiple Disabilities (PIMD) Using Machine Learning Algorithms
Vocal-Tract Models to Visualize the Airstream of Human Breath and Droplets While Producing Speech
VocalTurk: Exploring Feasibility of Crowdsourced Speaker Identification

« prev Page 19/20 next »