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
Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion
Non-native Perception of Japanese Singleton/Geminate Contrasts: Comparison of Mandarin and Mongolian Speakers Differing in Japanese Experience
Non-Parallel Voice Conversion for ASR Augmentation
Nonwords Pronunciation Classification in Language Development Tests for Preschool Children
Normalization of code-switched text for speech synthesis
Norm-constrained Score-level Ensemble for Spoofing Aware Speaker Verification
Novel Augmentation Schemes for Device Robust Acoustic Scene Classification
NRI-FGSM: An Efficient Transferable Adversarial Attack for Speaker Recognition Systems
NTF of Spectral and Spatial Features for Tracking and Separation of Moving Sound Sources in Spherical Harmonic Domain
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk in the Stereophonic Case
OCTRA – An Innovative Approach to Orthographic Transcription
Oktoechos Classification in Liturgical Music Using SBU-LSTM/GRU
On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer
On Breathing Pattern Information in Synthetic Speech
On Combining Global and Localized Self-Supervised Models of Speech
On-demand compute reduction with stochastic wav2vec 2.0
One-Shot Speaker Adaptation Based on Initialization by Generative Adversarial Networks for TTS
One-step models in pitch perception: Experimental evidence from Japanese
On joint training with interfaces for spoken language understanding
Online Continual Learning of End-to-End Speech Recognition Models
Online Learning of Open-set Speaker Identification by Active User-registration
Online Speaker Diarization with Core Samples Selection
Online Target Speaker Voice Activity Detection for Speaker Diarization
On Metric Learning for Audio-Text Cross-Modal Retrieval
On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
On-the-fly ASR Corrections with Audio Exemplars
On the Prediction Network Architecture in RNN-T for ASR
On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement
On the Use of Deep Mask Estimation Module for Neural Source Separation Systems
OpenASR21: The Second Open Challenge for Automatic Speech Recognition of Low-Resource Languages
Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset
Optimal thyroplasty implant shape and stiffness for treatment of acute unilateral vocal fold paralysis: Evidence from a canine in vivo phonation model
Optimization of Deep Neural Network (DNN) Speech Coder Using a Multi Time Scale Perceptual Loss Function
ORCA-WHISPER: An Automatic Killer Whale Sound Type Generation Toolkit Using Deep Learning
Oriental Language Recognition (OLR) 2021: Summary and Analysis
Orofacial somatosensory inputs in speech perceptual training modulate speech production
OSSEM: one-shot speaker adaptive speech enhancement using meta learning
Overlapped Frequency-Distributed Network: Frequency-Aware Voice Spoofing Countermeasure
Overlapped speech and gender detection with WavLM pre-trained features
Overlapped Speech Detection in Broadcast Streams Using X-vectors
Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
Paraguayan Guarani: Tritonal pitch accent and Accentual Phrase
Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition
Pay More Attention to History: A Context Modeling Strategy for Conversational Text-to-SQL
PEAF: Learnable Power Efficient Analog Acoustic Features for Audio Recognition
Perceived prominence and downstep in Japanese
PercepNet+: A Phase and SNR Aware PercepNet for Real-Time Speech Enhancement
PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of /ɹ/

« prev Page 15/23 next »