已发表成果:
WOK 论文 83 篇;中文核心 12 篇;其它论文 1 篇;专利发明 6 个;
Reverberation aware deep learning for environment tolerant microphone array DOA estimation
When Speaker Recognition Meets Noisy Labels: Optimizations for Front-ends and Back-ends
Deep joint learning for language recognition
MULTI-FEATURE LEARNING WITH CANONICAL CORRELATION ANALYSIS CONSTRAINT FOR TEXT-INDEPENDENT SPEAKER VERIFICATION
LIGHTSPEECH: LIGHTWEIGHT NON-AUTOREGRESSIVE MULTI-SPEAKER TEXT-TO-SPEECH
LIGHT-TTS: LIGHTWEIGHT MULTI-SPEAKER MULTI-LINGUAL TEXT-TO-SPEECH
END-TO-END MULTI-ACCENT SPEECH RECOGNITION WITH UNSUPERVISED ACCENT MODELLING
ASV-SUBTOOLS: OPEN SOURCE TOOLKIT FOR AUTOMATIC SPEAKER VERIFICATION
Automatic Error Correction for Speaker Embedding Learning with Noisy Labels
An Integrated Framework for Two-pass Personalized Voice Trigger
Additive Phoneme-aware Margin Softmax Loss for Language Recognition
Phoneme-aware and Channel-wise Attentive Learning for Text Dependent Speaker Verification
Real-time End-to-End Monaural Multi-speaker Speech Recognition
Oriental Language Recognition (OLR) 2020: Summary and Analysis
OLR 2021 Challenge: Datasets, Rules and Baselines
基于端到端的多语种语音识别研究
信号处理,1003-0530,2021-10-15.