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
Perceptual Characteristics Based Multi-objective Model for Speech Enhancement
Perceptual Contrast Stretching on Target Feature for Speech Enhancement
Perceptual Evaluation of Penetrating Voices through a Semantic Differential Method
Performance Improvement of Speech Emotion Recognition by Neutral Speech Detection Using Autoencoder and Intermediate Representation
Personalized Acoustic Echo Cancellation for Full-duplex Communications
Personalized Keyword Spotting through Multi-task Learning
Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Pharyngealization in Amazigh: Acoustic and articulatory marking over time
Phase Vocoder For Time Stretch Based On Center Frequency Estimation
PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification
Phonetic Analysis of Self-supervised Representations of English Speech
Phonetic Embedding for ASR Robustness in Entity Resolution
Phonetic erosion and information structure in function words: the case of mia
PISA: PoIncaré Saliency-Aware Interpolative Augmentation
PISA: PoIncaré Saliency-Aware Interpolative Augmentation
PLCNet: Real-time Packet Loss Concealment with Semi-supervised Generative Adversarial Network
Plugging a neural phoneme recognizer into a simple language model: a workflow for low-resource setting
pMCT: Patched Multi-Condition Training for Robust Speech Recognition
PM-MMUT: Boosted Phone-mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition
PodcastMix: A dataset for separating music and speech in podcasts
PoeticTTS - Controllable Poetry Reading for Literary Studies
Positional Encoding for Capturing Modality Specific Cadence for Emotion Detection
Practical Over-the-air Perceptual AcousticWatermarking
Predicting Emotional Intensity in Political Debates via Non-verbal Signals
Predicting label distribution improves non-intrusive speech quality estimation
Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks
Predicting Speech Intelligibility using the Spike Acativity Mutual Information Index
Predicting VQVAE-based Character Acting Style from Quotation-Annotated Text for Audiobook Speech Synthesis
Prediction of L2 speech proficiency based on multi-level linguistic features
Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data
Preventing sensitive-word recognition using self-supervised learning to preserve user-privacy for automatic speech recognition
PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification
Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings
Probing phoneme, language and speaker information in unsupervised speech representations
Probing speech emotion recognition transformers for linguistic knowledge
Production characteristics of obstruents in WaveNet and older TTS systems
Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
Production Strategies of Vocal Attitudes
Prompt-based Re-ranking Language Model for ASR
Pronunciation Dictionary-Free Multilingual Speech Synthesis by Combining Unsupervised and Supervised Phonetic Representations
Prosodic alignment for off-screen automatic dubbing
Prosodic Information in Dialect Identification of a Tonal Language: The case of Ao
Prototypical speaker-interference loss for target voice separation using non-parallel audio samples
Pruned RNN-T for fast, memory-efficient ASR training
Pseudo Label Is Better Than Human Label
Pushing the limits of raw waveform speaker recognition
QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer
QDPN - Quasi-dual-path Network for single-channel Speech Separation
Qualitative Evaluation of Language Model Rescoring in Automatic Speech Recognition

« prev Page 16/23 next »