Interspeech 2022

1,122 papers
Interspeech 2022 featured research focused on end-to-end learning from raw audio waveforms and improving robust speech processing in out-of-distribution environments. Technical developments emphasized architectural innovations, such as asymmetric convolutions for time-frequency processing and the integration of local and global contexts. Multi-resolution architectures and precise temporal grounding for sound event detection were also prominent themes during this edition. The year's contributions addressed diverse applications, including the automatic detection of speech sound disorders in children and privacy-preserving techniques for automatic speech recognition using self-supervised learning. Research also explored speaker identification challenges, such as mitigating within-household confusability through graph-based multi-view fusion. Other work included advancements in speech enhancement via cross-layer similarity knowledge distillation and any-to-any voice conversion using contrastive predictive coding frameworks. Prolific contributors to this edition included researchers such as Chi-Chun Lee, Yu Tsao, and Hsin-Min Wang.

Top Research Directions

Research directions most represented by Interspeech 2022 papers.

Learning High-Level Acoustic Structures from Unlabeled Audio 41
Overcoming Data Scarcity in Low-Resource Speech Recognition 28
Integrating Local and Global Context in Speech Architectures 27
Balancing Latency and Accuracy in Streaming Speech Recognition 25
Partitioning Variance with Linear Mixed Effects Models 21
Generalization to Unseen Acoustic Environments 20
Zero Shot Speaker Generalization for Speech Synthesis 20
The Perceptual Evaluation Gap in Generative Audio 20
Joint Optimization of Speech Enhancement and Recognition 18
Fine-Grained Prosodic Control for Expressive Speech Synthesis 18
The Single Speaker Generalization Bottleneck in Speech Synthesis 18
Complex Spectral Mapping for Phase Aware Signal Reconstruction 17
Robust Natural Language Understanding for Noisy Speech Transcripts 17
Resolving Overlapping Speech in Multi-Speaker Audio 17
Parameter Efficient Speech and Audio Processing 16

Top Authors

AuthorPapers
Shinji Watanabe23
Helen M. Meng14
Hung-yi Lee10
Zhiyong Wu10
Joon-Hyuk Chang9
Yanmin Qian9
Yonghong Yan9
Haizhou Li8
Jinyu Li8
Longbiao Wang8
Jing Xiao7
Lei Xie7
Yu Tsao7
Alan Black6
Jesus Villalba6
Joseph Keshet6
Jun Du6
Michael Auli6
Najim Dehak6
Yu Wu6

Impactful Papers

Papers from Interspeech 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Mixup regularization strategies for spoofing countermeasure system
Model Compression by Iterative Pruning with Knowledge Distillation and Its Application to Speech Enhancement
Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data
Modelling Turn-taking in Multispeaker Parties for Realistic Data Simulation
Monaural Speech Enhancement Based on Spectrogram Decomposition for Convolutional Neural Network-sensitive Feature Extraction
Monoaural Speech Enhancement Using a Nested U-Net with Two-Level Skip Connections
MOS Prediction Network for Non-intrusive Speech Quality Assessment in Online Conferencing
MOSRA: Joint Mean Opinion Score and Room Acoustics Speech Quality Assessment
MSDWild: Multi-modal Speaker Diarization Dataset in the Wild
MSR-NV: Neural Vocoder Using Multiple Sampling Rates
MTI-Net: A Multi-Target Speech Intelligibility Prediction Model
Multi-Channel Far-Field Speaker Verification with Large-Scale Ad-hoc Microphone Arrays
Multichannel Speech Separation with Narrow-band Conformer
Multi-class AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data
Multi-Corpus Speech Emotion Recognition for Unseen Corpus Using Corpus-Wise Weights in Classification Loss
Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning
Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition
Multilingual and Multimodal Abuse Detection
Multimodal Clustering with Role Induced Constraints for Speaker Diarization
Multimodal Depression Severity Score Prediction Using Articulatory Coordination Features and Hierarchical Attention Based Text Embeddings
Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation
Multimodal Persuasive Dialogue Corpus using Teleoperated Android
Multi-Path GMM-MobileNet Based on Attack Algorithms and Codecs for Synthetic Speech and Deepfake Detection
Multiple Enhancements to LSTM for Learning Emotion-Salient Features in Speech Emotion Recognition
Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Multi-scale Speaker Diarization with Dynamic Scale Weighting
Multi-source wideband DOA estimation method by frequency focusing and error weighting
Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
Multi-Task End-to-End Model for Telugu Dialect and Speech Recognition
Multitask Learning for Low Resource Spoken Language Understanding
Multi-Type Outer Product-Based Fusion of Respiratory Sounds for Detecting COVID-19
Multi-View Attention Transfer for Efficient Speech Enhancement
MusicNet: Compact Convolutional Neural Network for Real-time Background Music Detection
Muskits: an End-to-end Music Processing Toolkit for Singing Voice Synthesis
Nasal Coda Loss in the Chengdu Dialect of Mandarin: Evidence from RT-MRI
NAS-SCAE: Searching Compact Attention-based Encoders For End-to-end Automatic Speech Recognition
NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling
NAS-VAD: Neural Architecture Search for Voice Activity Detection
Native phonotactic interference in L2 vowel processing: Mouse-tracking reveals cognitive conflicts during identification
Negative Guided Abstractive Dialogue Summarization
NeMo Open Source Speaker Diarization System
NESC: Robust Neural End-2-End Speech Coding with GANs
Neural correlates of acoustic and semantic cues during speech segmentation in French
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments
Neural Vocoder is All You Need for Speech Super-resolution
Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Non-contrastive self-supervised learning of utterance-level speech representations
Non-intrusive Speech Intelligibility Metric Prediction for Hearing Impaired Individuals
Non-intrusive Speech Quality Assessment with a Multi-Task Learning based Subband Adaptive Attention Temporal Convolutional Neural Network

« prev Page 14/23 next »