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
Radio2Speech: High Quality Speech Recovery from Radio Frequency Signals
RaDur: A Reference-aware and Duration-robust Network for Target Sound Detection
Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
RCT: Random consistency training for semi-supervised sound event detection
Real-Time Monitoring of Silences in Contact Center Conversations
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Recent improvements of ASR models in the face of adversarial attacks
Recording and timing vocal responses in online experimentation
Recurrent multi-head attention fusion network for combining audio and text for speech emotion recognition
Reducing Domain mismatch in Self-supervised speech pre-training
Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
reducing multilingual context confusion for end-to-end code-switching automatic speech recognition
Reducing Offensive Replies in Open Domain Dialogue Systems
Reducing uncertainty at the score-to-LR stage in likelihood ratio-based forensic voice comparison using automatic speaker recognition systems
RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses
Refining DNN-based Mask Estimation using CGMM-based EM Algorithm for Multi-channel Noise Reduction
RefTextLAS: Reference Text Biased Listen, Attend, and Spell Model For Accurate Reading Evaluation
Regularizing Transformer-based Acoustic Models by Penalizing Attention Weights
Relating the fundamental frequency of speech with EEG using a dilated convolutional network
Relationship between the acoustic time intervals and tongue movements of German diphthongs
Relative Acoustic Features for Distance Estimation in Smart-Homes
Reliability criterion based on learning-phase entropy for speaker recognition with neural network
Reliable Visualization for Deep Speaker Recognition
Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Representing 'how you say' with 'what you say': English corpus of focused speech and text reflecting corresponding implications
ResectNet: An Efficient Architecture for Voice Activity Detection on Mobile Devices
Residual Language Model for End-to-end Speech Recognition
Response Timing Estimation for Spoken Dialog System using Dialog Act Estimation
RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model
Revisiting visuo-spatial processing in individuals with congenital amusia
REYD – The First Yiddish Text-to-Speech Dataset and System
RNN-T lattice enhancement by grafting of pruned paths
RNN Transducers for Named Entity Recognition with constraints on alignment for understanding medical conversations
Robust Cough Feature Extraction and Classification Method for COVID-19 Cough Detection Based on Vocalization Characteristics
Robust End-to-end Speaker Diarization with Generic Neural Clustering
Robust Pitch Estimation Using Multi-Branch CNN-LSTM and 1-Norm LP Residual
Robust Self-Supervised Audio-Visual Speech Recognition
SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
SAQAM: Spatial Audio Quality Assessment Metric
SA-SASV: An End-to-End Spoof-Aggregated Spoofing-Aware Speaker Verification System
SASV 2022: The First Spoofing-Aware Speaker Verification Challenge
SASV Based on Pre-trained ASV System and Integrated Scoring Module
SATTS: Speaker Attractor Text to Speech, Learning to Speak by Learning to Separate
SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition
Scaling ASR Improves Zero and Few Shot Learning
Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?
ScoutWav: Two-Step Fine-Tuning on Self-Supervised Automatic Speech Recognition for Low-Resource Environments
Selective Pseudo-labeling and Class-wise Discriminative Fusion for Sound Event Detection
Self-Distillation Based on High-level Information Supervision for Compressing End-to-End ASR Model

« prev Page 17/23 next »