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
Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations
Investigating the Impact of Crosslingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition
Investigating the Impact of Speech Compression on the Acoustics of Dysarthric Speech
Investigating the influence of personality on acoustic-prosodic entrainment
Investigation into Target Speaking Rate Adaptation for Voice Conversion
Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition
Investigation on the Band Importance of Phase-aware Speech Enhancement
Isochronous is beautiful? Syllabic event detection in a neuro-inspired oscillatory model is facilitated by isochrony in speech
Isochrony-Aware Neural Machine Translation for Automatic Dubbing
Iterative Sound Source Localization for Unknown Number of Sources
Japanese ASR-Robust Pre-trained Language Model with Pseudo-Error Sentences Generated by Grapheme-Phoneme Conversion
JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Joint Encoder-Decoder Self-Supervised Pre-training for ASR
Joint Estimation of Direction-of-Arrival and Distance for Arrays with Directional Sensors based on Sparse Bayesian Learning
Joint Modeling of Multi-Sample and Subband Signals for Fast Neural Vocoding on CPU
Joint Neural AEC and Beamforming with Double-Talk Detection
Joint Optimization of Sampling Rate Offsets Based on Entire Signal Relationship Among Distributed Microphones
Joint Optimization of the Module and Sign of the Spectral Real Part Based on CRN for Speech Denoising.
Karaoker: Alignment-free singing voice synthesis with speech training data
KaraTuner: Towards End-to-End Natural Pitch Correction for Singing Voice in Karaoke
Keyword Spotting with Synthetic Data using Heterogeneous Knowledge Distillation
kidsTALC: A Corpus of 3- to 11-year-old German Children's Connected Natural Speech
Knowledge Distillation For CTC-based Speech Recognition Via Consistent Acoustic Representation Learning
Knowledge distillation for In-memory keyword spotting model
Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer
Knowledge of accent differences can be used to predict speech recognition
Knowledge Transfer and Distillation from Autoregressive to Non-Autoregessive Speech Recognition
KSC2: An Industrial-Scale Open-Source Kazakh Speech Corpus
K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables
L2-GEN: A Neural Phoneme Paraphrasing Approach to L2 Speech Synthesis for Mispronunciation Diagnosis
Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning
LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems
Language-specific Characteristic Assistance for Code-switching Speech Recognition
Language-specific interactions of vowel discrimination in noise
Large-Scale Streaming End-to-End Speech Translation with Neural Transducers
Latency Control for Keyword Spotting
LCSM: A Lightweight Complex Spectral Mapping Framework for Stereophonic Acoustic Echo Cancellation
Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher
Learnable Sparse Filterbank for Speaker Verification
Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Learning from human perception to improve automatic speaker verification in style-mismatched conditions
Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT
Learning neural audio features without supervision
Learning Noise-independent Speech Representation for High-quality Voice Conversion for Noisy Target Speakers
Learning to rank with BERT-based confidence models in ASR rescoring
Learning Under Label Noise for Robust Spoken Language Understanding systems
Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR

« prev Page 12/23 next »