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
Text Augmentation for Language Models in High Error Recognition Scenario
The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results
The Application of Learnable STRF Kernels to the 2021 Fearless Steps Phase-03 SAD Challenge
The CSTR System for Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages
The DiCOVA 2021 Challenge — An Encoder-Decoder Approach for COVID-19 Recognition from Coughing Audio
The Effect of Silence and Dual-Band Fusion in Anti-Spoofing System
The Energy and Carbon Footprint of Training End-to-End Speech Recognizers
The Four-Way Classification of Stops with Voicing and Aspiration for Non-Native Speech Evaluation
The ID R&D System Description for Short-Duration Speaker Verification Challenge 2021
The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech
The Impact of Forced-Alignment Errors on Automatic Pronunciation Evaluation
The Impact of Intent Distribution Mismatch on Semi-Supervised Spoken Language Understanding
The Influence of Parallel Processing on Illusory Vowels
The INGENIOUS Multilingual Operations App
The Interaction of Word Complexity and Word Duration in an Agglutinative Language
The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates
The LF Model in the Frequency Domain for Glottal Airflow Modelling Without Aliasing Distortion
The LIUM Human Active Correction Platform for Speaker Diarization
ThemePro 2.0: Showcasing the Role of Thematic Progression in Engaging Human-Computer Interaction
The Multilingual TEDx Corpus for Speech Recognition and Translation
The Pacific Expansion: Optimizing Phonetic Transcription of Archival Corpora
The Phonetic Footprint of Covid-19?
The SJTU System for Short-Duration Speaker Verification Challenge 2021
The Sogou System for Short-Duration Speaker Verification Challenge 2021
The TAL System for the INTERSPEECH2021 Shared Task on Automatic Speech Recognition for Non-Native Childrens Speech
The Third DIHARD Diarization Challenge
The TNT Team System Descriptions of Cantonese and Mongolian for IARPA OpenASR20
The Zero Resource Speech Challenge 2021: Spoken Language Modelling
Three-Class Overlapped Speech Detection Using a Convolutional Recurrent Neural Network
Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-Trained DNN-HMM-Based Acoustic-Phonetic Model
Tied & Reduced RNN-T Decoder
Time Delay Estimation for Speaker Localization Using CNN-Based Parametrized GCC-PHAT Features
Time-Frequency Representation Learning with Graph Convolutional Network for Dialogue-Level Speech Emotion Recognition
Time-to-Event Models for Analyzing Reaction Time Sequences
Timing Generating Networks: Neural Network Based Precise Turn-Taking Timing Prediction in Multiparty Conversation
Token-Level Supervised Contrastive Learning for Punctuation Restoration
Toward Genre Adapted Closed Captioning
Towards an Accent-Robust Approach for ATC Communications Transcription
Towards Automatic Speech Recognition for People with Atypical Speech
Towards Automatic Speech to Sign Language Generation
Towards Lifelong Learning of End-to-End ASR
Towards Multi-Scale Style Control for Expressive Speech Synthesis
Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR
Towards Simultaneous Machine Interpretation
Towards the Explainability of Multimodal Speech Emotion Recognition
Towards the Prediction of the Vocal Tract Shape from the Sequence of Phonemes to be Articulated
Toward Streaming ASR with Non-Autoregressive Insertion-Based Model
Towards Unsupervised Phone and Word Segmentation Using Self-Supervised Vector-Quantized Neural Networks
Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition
Transcribing Paralinguistic Acoustic Cues to Target Language Text in Transformer-Based Speech-to-Text Translation

« prev Page 18/20 next »