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
Self-Normalized Importance Sampling for Neural Language Modeling
Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition
SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling
Self-supervised Context-aware Style Representation for Expressive Speech Synthesis
Self supervised learning for robust voice cloning
Self-Supervised Learning with Multi-Target Contrastive Coding for Non-Native Acoustic Modeling of Mispronunciation Verification
Self-supervised Representation Fusion for Speech and Wearable Based Emotion Recognition
Self-supervised Speaker Diarization
Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction
Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE
Semantically Meaningful Metrics for Norwegian ASR Systems
Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling
Semi-supervised Acoustic and Language Modeling for Hindi ASR
Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
Separate What You Describe: Language-Queried Audio Source Separation
Separating Long-Form Speech with Group-wise Permutation Invariant Training
Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech
SepIt: Approaching a Single Channel Speech Separation Bound
SepTr: Separable Transformer for Audio Spectrogram Processing
Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization
SHAS: Approaching optimal Segmentation for End-to-End Speech Translation
SiDi KWS: A Large-Scale Multilingual Dataset for Keyword Spotting
SiD-WaveFlow: A Low-Resource Vocoder Independent of Prior Knowledge
Significance of single frequency filter for the development of children's KWS system
Similarity and Content-based Phonetic Self Attention for Speech Recognition
Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody
Simple and Effective Unsupervised Speech Synthesis
Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy
Single-channel speech enhancement using Graph Fourier Transform
SKYE: More than a conversational AI
Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning
Small Footprint Neural Networks for Acoustic Direction of Arrival Estimation
SNRi Target Training for Joint Speech Enhancement and Recognition
Soft-label Learn for No-Intrusive Speech Quality Assessment
SoftSpeech: Unsupervised Duration Model in FastSpeech 2
SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation
SoundDoA: Learn Sound Source Direction of Arrival and Semantics from Sound Raw Waveforms
Space-Efficient Representation of Entity-centric Query Language Models
Span Classification with Structured Information for Disfluency Detection in Spoken Utterances
Spatial-aware Speaker Diarizaiton for Multi-channel Multi-party Meeting
Spatial Loss for Unsupervised Multi-channel Source Separation
Speaker adaptation for Wav2vec2 based dysarthric ASR
Speaker- and Phone-aware Convolutional Transformer Network for Acoustic Echo Cancellation
Speaker Anonymization with Phonetic Intermediate Representations
Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction
Speaker conditioned acoustic modeling for multi-speaker conversational ASR

« prev Page 18/23 next »