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
Towards Cross-speaker Reading Style Transfer on Audiobook Dataset
Towards Disentangled Speech Representations
Towards Efficiently Learning Monotonic Alignments for Attention-based End-to-End Speech Recognition
Towards End-to-End Private Automatic Speaker Recognition
Towards Error-Resilient Neural Speech Coding
Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Swithboard Corpus
Towards high-fidelity singing voice conversion with acoustic reference and contrastive predictive coding
Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information
Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis
Toward Zero Oracle Word Error Rate on the Switchboard Benchmark
tPLCnet: Real-time Deep Packet Loss Concealment in the Time Domain Using a Short Temporal Context
Training and typological bias in ASR performance for world Englishes
Training Data Generation with DOA-based Selecting and Remixing for Unsupervised Training of Deep Separation Models
Training speaker embedding extractors using multi-speaker audio with unknown speaker boundaries
Training speaker recognition systems with limited data
Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks
Trajectories predicted by optimal speech motor control using LSTM networks
Transducer-based language embedding for spoken language identification
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping
Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus
Transfer Learning from Multi-Lingual Speech Translation Benefits Low-Resource Speech Recognition
Transformer-Based Automatic Speech Recognition with Auxiliary Input of Source Language Text Toward Transcribing Simultaneous Interpretation
Transformer-based quality assessment model for generalized user-generated multimedia audio content
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video
Transformer Networks for Non-Intrusive Speech Quality Prediction
Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis
Transport-Oriented Feature Aggregation for Speaker Embedding Learning
Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition
TRILLsson: Distilled Universal Paralinguistic Speech Representations
TriniTTS: Pitch-controllable End-to-end TTS without External Aligner
TRUNet: Transformer-Recurrent-U Network for Multi-channel Reverberant Sound Source Separation
TTS-by-TTS 2: Data-Selective Augmentation for Neural Speech Synthesis Using Ranking Support Vector Machine with Variational Autoencoder
Turn-Taking Prediction for Natural Conversational Speech
Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems
Two-Pass Low Latency End-to-End Spoken Language Understanding
Ultra-Low-Bitrate Speech Coding with Pretrained Transformers
Uncertainty Calibration for Deep Audio Classifiers
UNet-DenseNet for Robust Far-Field Speaker Verification
Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation
Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)
Unifying Cosine and PLDA Back-ends for Speaker Verification
UniKW-AT: Unified Keyword Spotting and Audio Tagging
Unsupervised Acoustic-to-Articulatory Inversion with Variable Vocal Tract Anatomy
Unsupervised Data Selection via Discrete Speech Representation for ASR
Unsupervised domain adaptation for speech recognition with unsupervised error correction
Unsupervised Inference of Physiologically Meaningful Articulatory Trajectories with VocalTractLab
Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals
Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free

« prev Page 21/23 next »