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.
Top Authors
Impactful Papers
Papers from Interspeech 2022 that shaped research clusters.
Foundational
Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation
foundational
Confidence Weighted Knowledge Distillati
Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speak
foundational
Intermediate Speech Representations for
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Repr
foundational
Aligning Augmentation Invariance with Do
Fast Grad-TTS: Towards Efficient Diffusion-Based Speech Generation on CPU
foundational
Compressing Diffusion Sampling Trajector
Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translatio
foundational
Dynamic Chunk Training for Flexible Late
Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
foundational
Generalizing Audio Deepfake Detection Ac
Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription
foundational
Intermediate Speech Representations for
Influential
Statistical and clinical utility of multimodal dialogue-based speech and facial metrics for Parkinso
influential
Quantifying Clinical Relevance Beyond St
Training and typological bias in ASR performance for world Englishes
influential
Automatic Speech Recognition as a Proxy
EdiTTS: Score-based Editing for Controllable Text-to-Speech
influential
Acoustic Boundary Discontinuities in Seg
BIT-MI Deep Learning-based Model to Non-intrusive Speech Quality Assessment Challenge in Online Conf
influential
Parameter Efficiency and Model Size Opti
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter
influential
Alignment Free Sequence Training with Co
Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE
influential
Recovering Articulatory Movements from S
Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model
influential
Contextual Biasing for End-to-End Speech
OSSEM: one-shot speaker adaptive speech enhancement using meta learning
influential
Personalizing Speech Models with Minimal
The CLIPS System for 2022 Spoofing-Aware Speaker Verification Challenge
influential
Detecting Audio Replay Attacks in Speake
Confidence Score Based Conformer Speaker Adaptation for Speech Recognition
influential
Bayesian Parameter Adaptation under Data
Papers
« prev Page 23/23