← Authors

Zhengkun Tian

14 papers · 2019–2024 · 3 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (5) πŸ—ΊοΈ Taxonomy Completionist (20) 🐝 Cross-Pollinator (11) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (3) 🀝 Dynamic Duo (11) πŸ—ƒοΈ Keyword Collector (62) ⚑ Prolific Year (6) πŸ’Ž Century Club (14)

Conferences

INTERSPEECH (12) ACL (1) IJCNLP (1)

Top co-authors

Jiangyan Yi (11) Jianhua Tao (11) Ye Bai (10) Zhengqi Wen (7) SHUAI ZHANG (5) Cunhang Fan (2) Yubo Chen (2) Haoxin Ma (2) Dianbo Sui (2) Chenglong Wang (2)

Keywords

speech recognition (4) automatic speech recognition (4) end-to-end speech recognition (3) end-to-end model (2) named entity recognition (2) knowledge distillation (2) fake audio detection (2) connectionist temporal classification (2) sequence labeling (2) multimodal learning (2) chinese language (2) attention mechanism (2) character error rate (2) speech processing (2) code-switching speech recognition (2) spoofing detection (1) keyword spotting (1) multitask learning (1) catastrophic forgetting (1) language model (1)

Papers

MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research INTERSPEECH 2024
reducing multilingual context confusion for end-to-end code-switching automatic speech recognition INTERSPEECH 2022
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues ACL 2021
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues IJCNLP 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
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization INTERSPEECH 2021
Focal Loss for Punctuation Prediction INTERSPEECH 2020
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
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition INTERSPEECH 2019
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