← Authors

Ye Bai

15 papers · 2019–2025 · 3 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) πŸ—ΊοΈ Taxonomy Completionist (22) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (3) πŸƒ Academic Marathon (6) 🀝 Dynamic Duo (11) 🧬 Topic Evolution πŸ’Ž Century Club (15) πŸ—ƒοΈ Keyword Collector (60) ❓ The Questioner πŸ”₯ Unstoppable (7)

Conferences

INTERSPEECH (13) EMNLP (1) ICLR (1)

Top co-authors

Jiangyan Yi (11) Jianhua Tao (11) Zhengkun Tian (10) Zhengqi Wen (8) SHUAI ZHANG (4) Cunhang Fan (2) Tao Wang (2) Haoxin Ma (2) Chenglong Wang (2) Zhuo Zhang (2)

Keywords

knowledge distillation (3) automatic speech recognition (3) speech recognition (3) parameter efficiency (2) model compression (2) end-to-end model (2) character error rate (2) end-to-end speech recognition (2) fake audio detection (2) connectionist temporal classification (2) attention mechanism (1) visual grounding (1) keyword spotting (1) spoofing detection (1) decision making (1) catastrophic forgetting (1) cross-modal learning (1) latent representation (1) sequence labeling (1) audio source separation (1)

Papers

Discrete Minds in a Continuous World: Do Language Models Know Time Passes? EMNLP 2025
PolyVoice: Language Models for Speech to Speech Translation ICLR 2024
TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking INTERSPEECH 2024
Image-driven Audio-visual Universal Source Separation INTERSPEECH 2023
Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition INTERSPEECH 2022
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization INTERSPEECH 2021
End-to-End Spelling Correction Conditioned on Acoustic Feature for Code-Switching Speech Recognition INTERSPEECH 2021
Continual Learning for Fake Audio Detection INTERSPEECH 2021
Half-Truth: A Partially Fake Audio Detection Dataset INTERSPEECH 2021
Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition INTERSPEECH 2020
Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition INTERSPEECH 2020
Focal Loss for Punctuation Prediction INTERSPEECH 2020
A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting INTERSPEECH 2019
Self-Attention Transducers for End-to-End Speech Recognition INTERSPEECH 2019
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition INTERSPEECH 2019