2012-09--现在 中国科学院自动化研究所
2013-09--2019-01 中国科学院自动化研究所 博士
2007-09--2009-12 浙江大学 硕士
2002-09--2006-06 湖南师范大学 学士
语音识别,多模态大模型,博弈智能
2022-01-01至2024-12-31 算法工具包研发
2018-08-01至2021-07-31 基于云计算的移动办公智能交互技术与系统
(1) CIF-BASED COLLABORATIVE DECODING FOR END-TO-END CONTEXTUAL SPEECH RECOGNITION, 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, 第 3 作者
(2) Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition, IEEE SIGNAL PROCESSING LETTERS, 2021, 第 2 作者
(3) TWO-STAGE PRE-TRAINING FOR SEQUENCE TO SEQUENCE SPEECH RECOGNITION, IJCNN, 2021, 第 2 作者
(4) Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin, 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6, 2018, 第 2 作者
(5) A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese, NEURAL INFORMATION PROCESSING (ICONIP 2018), PT V, 2018, 通讯作者
(6) Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese, INTERSPEECH, 2018, 通讯作者
(7) Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling, ICONIP2017, 2017, 第 3 作者
(8) Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition, 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6, 2017, 通讯作者
(1)端到端的在线语音检测与识别方法、系统及设备, 发明专利, 2022, 第 1 作者, 专利号: CN112951213B
(2)一种语音文本联合预训练方法及系统, 发明专利, 2022, 第 1 作者, 专利号: 202210346308.6
(3)低资源多语言的语音识别模型、语音识别方法, 发明专利, 2019, 第 1 作者, 专利号: CN110428818A