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
Effects of Voice Type and Task on L2 Learners’ Awareness of Pronunciation Errors
Efficient and Stable Adversarial Learning Using Unpaired Data for Unsupervised Multichannel Speech Separation
Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-End Speech Recognition
EfficientSing: A Chinese Singing Voice Synthesis System Using Duration-Free Acoustic Model and HiFi-GAN Vocoder
Efficient Weight Factorization for Multilingual Speech Recognition
Emitting Word Timings with HMM-Free End-to-End System in Automatic Speech Recognition
EML Online Speech Activity Detection for the Fearless Steps Challenge Phase-III
Emotional Prosody Control for Speech Generation
Emotion Carrier Recognition from Personal Narratives
Emotion Recognition from Speech Using wav2vec 2.0 Embeddings
EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model
Empirical Analysis of Generalized Iterative Speech Separation Networks
End-to-End Audio-Visual Speech Recognition for Overlapping Speech
End-to-End Cross-Lingual Spoken Language Understanding Model with Multilingual Pretraining
End-to-End Language Diarization for Bilingual Code-Switching Speech
End-to-End Neural Diarization: From Transformer to Conformer
End-to-End Open Vocabulary Keyword Search
End-to-End Optimized Multi-Stage Vector Quantization of Spectral Envelopes for Speech and Audio Coding
End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning
End-to-End Speaker-Attributed ASR with Transformer
End-To-End Speaker Segmentation for Overlap-Aware Resegmentation
End-to-End Speech Separation Using Orthogonal Representation in Complex and Real Time-Frequency Domain
End-to-End Speech Translation via Cross-Modal Progressive Training
End-to-End Spelling Correction Conditioned on Acoustic Feature for Code-Switching Speech Recognition
End-to-End Spoken Language Understanding for Generalized Voice Assistants
End to End Transformer-Based Contextual Speech Recognition Based on Pointer Network
End-to-End Transformer-Based Open-Vocabulary Keyword Spotting with Location-Guided Local Attention
Energy-Friendly Keyword Spotting System Using Add-Based Convolution
Enhancing Semantic Understanding with Self-Supervised Methods for Abstractive Dialogue Summarization
Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis
Enriching Source Style Transfer in Recognition-Synthesis Based Non-Parallel Voice Conversion
Enrollment-Less Training for Personalized Voice Activity Detection
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
Estimating Articulatory Movements in Speech Production with Transformer Networks
Ethical and Technological Challenges of Conversational AI
ETLT 2021: Shared Task on Automatic Speech Recognition for Non-Native Children’s Speech
Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization
Evaluating the Extrapolation Capabilities of Neural Vocoders to Extreme Pitch Values
Evaluating the Vulnerability of End-to-End Automatic Speech Recognition Models to Membership Inference Attacks
Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models
Event Specific Attention for Polyphonic Sound Event Detection
Excitation Source Feature Based Dialect Identification in Ao — A Low Resource Language
Explaining Deep Learning Models for Speech Enhancement
Exploration of Welsh English Pre-Aspiration: How Wide-Spread is it?
Explore wav2vec 2.0 for Mispronunciation Detection
Exploring Emotional Prototypes in a High Dimensional TTS Latent Space
Exploring Targeted Universal Adversarial Perturbations to End-to-End ASR Models
Exploring the Potential of Lexical Paraphrases for Mitigating Noise-Induced Comprehension Errors
Exploring wav2vec 2.0 on Speaker Verification and Language Identification
Expressive Latvian Speech Synthesis for Dialog Systems

« prev Page 7/20 next »