Some Publications
- Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech RecognitionIn Proc. Interspeech 2022 2022
- Half-Truth: A Partially Fake Audio Detection DatasetIn Proc. Interspeech 2021 2021
- Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERTIEEE/ACM Transactions on Audio, Speech, and Language Processing 2021
- Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only DataIEEE/ACM Transactions on Audio, Speech, and Language Processing 2021
- Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech RecognitionIn Proc. Interspeech 2020 2020
- A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword SpottingIn Proc. Interspeech 2019 2019
- Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech RecognitionIn Proc. Interspeech 2019 2019
- Voice Activity Detection Based on Time-Delay Neural NetworksIn 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 2019
- A Public Chinese Dataset for Language Model AdaptationJournal of Signal Processing Systems 2019
- CLMAD: A Chinese Language Model Adaptation DatasetIn 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP) 2018
- End-to-end keywords spotting based on connectionist temporal classification for MandarinIn 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP) 2016