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
Improve Speech Enhancement using Perception-High-Related Time-Frequency Loss
Improving ASR Robustness in Noisy Condition Through VAD Integration
Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model
Improving Data Driven Inverse Text Normalization using Data Augmentation and Machine Translation
Improving Deliberation by Text-Only and Semi-Supervised Training
Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation
Improving GAN-based vocoder for fast and high-quality speech synthesis
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech
Improving Language Identification of Accented Speech
Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information
Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment
Improving Phonetic Transcriptions of Children's Speech by Pronunciation Modelling with Constrained CTC-Decoding
Improving Rare Word Recognition with LM-aware MWER Training
Improving Recognition of Out-of-vocabulary Words in E2E Code-switching ASR by Fusing Speech Generation Methods
Improving Speech Emotion Recognition Through Focus and Calibration Attention Mechanisms
Improving Speech Emotion Recognition Using Self-Supervised Learning with Domain-Specific Audiovisual Tasks
Improving Speech Enhancement through Fine-Grained Speech Characteristics
Improving Spoken Language Understanding with Cross-Modal Contrastive Learning
Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
Improving Target Sound Extraction with Timestamp Information
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism
Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention
Improving Voice Trigger Detection with Metric Learning
Incorporating Dual-Aware with Hierarchical Interactive Memory Networks for Task-Oriented Dialogue
Incremental Layer-Wise Self-Supervised Learning for Efficient Unsupervised Speech Domain Adaptation On Device
Incremental learning for RNN-Transducer based speech recognition models
Independence-based Joint Dereverberation and Separation with Neural Source Model
Induce Spoken Dialog Intents via Deep Unsupervised Context Contrastive Clustering
InQSS: a speech intelligibility and quality assessment model using a multi-task learning network
Integrating Discrete Word-Level Style Variations into Non-Autoregressive Acoustic Models for Speech Synthesis
Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings
Intent classification using pre-trained language agnostic embeddings for low resource languages
Interactive Auido-text Representation for Automated Audio Captioning with Contrastive Learning
Interactive Co-Learning with Cross-Modal Transformer for Audio-Visual Emotion Recognition
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR
Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition
Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR
Interpretabilty of Speech Emotion Recognition modelled using Self-Supervised Speech and Text Pre-Trained Embeddings
Interpretable dysarthric speaker adaptation based on optimal-transport
Interrelate Training and Searching: A Unified Online Clustering Framework for Speaker Diarization
INTERSPEECH 2022 Audio Deep Packet Loss Concealment Challenge
Intra-speaker phonetic variation in read speech: comparison with inter-speaker variability in a controlled population
Introducing Auxiliary Text Query-modifier to Content-based Audio Retrieval
Investigating Parameter Sharing in Multilingual Speech Translation
Investigating perception of spoken dialogue acceptability through surprisal
Investigating phonetic convergence of laughter in conversation
Investigating Prosodic Variation in British English Varieties using ProPer
Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition

« prev Page 11/23 next »