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
Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data
Speaker recognition-assisted robust audio deepfake detection
Speaker-Specific Utterance Ensemble based Transfer Attack on Speaker Identification
Speaker Trait Enhancement for Cochlear Implant Users: A Case Study for Speaker Emotion Perception
Speaking Rate Control of end-to-end TTS Models by Direct Manipulation of the Encoder's Output Embeddings
Speak Like a Professional: Increasing Speech Intelligibility by Mimicking Professional Announcer Voice with Voice Conversion
SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping
Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech
Spectro-Temporal SubNet for Real-Time Monaural Speech Denoising and Dereverberation
Speech2Slot: A Limited Generation Framework with Boundary Detection for Slot Filling from Speech
Speech Acoustics in Mild Cognitive Impairment and Parkinson's Disease With and Without Concurrent Drawing Tasks
Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression
Speech Audio Corrector: using speech from non-target speakers for one-off correction of mispronunciations in grapheme-input text-to-speech
Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation
Speech Emotion Recognition in the Wild using Multi-task and Adversarial Learning
Speech Emotion Recognition via Generation using an Attention-based Variational Recurrent Neural Network
Speech Enhancement with Fullband-Subband Cross-Attention Network
Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain
SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning
SpeechFormer: A Hierarchical Efficient Framework Incorporating the Characteristics of Speech
Speech imitation skills predict automatic phonetic convergence: a GMM-UBM study on L2
Speech intelligibility of simulated hearing loss sounds and its prediction using the Gammachirp Envelope Similarity Index (GESI)
Speech Intelligibility Prediction for Hearing-Impaired Listeners with the LEAP Model
Speech Modification for Intelligibility in Cochlear Implant Listeners: Individual Effects of Vowel- and Consonant-Boosting
SpeechPainter: Text-conditioned Speech Inpainting
Speech Pre-training with Acoustic Piece
Speech Quality Assessment through MOS using Non-Matching References
Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation
Speech Separation for an Unknown Number of Speakers Using Transformers With Encoder-Decoder Attractors
Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning
SPLICEOUT: A Simple and Efficient Audio Augmentation Method
Spoken Dialogue System for Call Centers with Expressive Speech Synthesis
Spoken-Text-Style Transfer with Conditional Variational Autoencoder and Content Word Storage
Spoofed speech from the perspective of a forensic phonetician
Spoofing-Aware Attention based ASV Back-end with Multiple Enrollment Utterances and a Sampling Strategy for the SASV Challenge 2022
Spoofing-Aware Speaker Verification by Multi-Level Fusion
Squashed Weight Distribution for Low Bit Quantization of Deep Models
State & Trait Measurement from Nonverbal Vocalizations: A Multi-Task Joint Learning Approach
Statistical and clinical utility of multimodal dialogue-based speech and facial metrics for Parkinson's disease assessment
Steering vector correction in MVDR beamformer for speech enhancement
Strategies for developing a Conversational Speech Dataset for Text-To-Speech Synthesis
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Streamable Speech Representation Disentanglement and Multi-Level Prosody Modeling for Live One-Shot Voice Conversion
Streaming Align-Refine for Non-autoregressive Deliberation
Streaming Automatic Speech Recognition with Re-blocking Processing Based on Integrated Voice Activity Detection
Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
Streaming Intended Query Detection using E2E Modeling for Continued Conversation
Streaming model for Acoustic to Articulatory Inversion with transformer networks
Streaming Multi-Talker ASR with Token-Level Serialized Output Training

« prev Page 19/23 next »