CASIA OpenIR

Browse/Search Results:  1-5 of 5 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
会议场景智能语音处理技术研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2022
Authors:  范志赟
Adobe PDF(3323Kb)  |  Favorite  |  View/Download:50/2  |  Submit date:2022/09/15
会议场景,语音识别,说话人转换点检测,说话人自适应  
Sequence-level Speaker Change Detection with Difference-based Continuous Integrate-and-fire 期刊论文
Signal Processing Letters, 2022, 页码: 1551-1554
Authors:  Fan ZY(范志赟);  Dong LH(董林昊);  Cai M(蔡猛);  Ma ZJ(马泽君);  Xu B(徐波)
Adobe PDF(404Kb)  |  Favorite  |  View/Download:20/1  |  Submit date:2022/09/17
TWO-STAGE PRE-TRAINING FOR SEQUENCE TO SEQUENCE SPEECH RECOGNITION 会议论文
, 线上会议, 2021-7-18
Authors:  Fan ZY(范志赟);  Zhou SY(周世玉);  Xu B(徐波)
Adobe PDF(230Kb)  |  Favorite  |  View/Download:17/1  |  Submit date:2022/09/17
pre-training  speech recognition  encoder-decoder  sequence-to-sequence  
Exploring wav2vec 2.0 on speaker verification and language identification 会议论文
, 线上会议, 2021-8-30
Authors:  Fan ZY(范志赟);  Li M(李蒙);  Zhou SY(周世玉);  Xu B(徐波)
Adobe PDF(2081Kb)  |  Favorite  |  View/Download:21/2  |  Submit date:2022/09/17
self-supervised  speaker verification  language identification  multi-task learning  wav2vec 2.0  
SPEAKER-AWARE SPEECH-TRANSFORMER 会议论文
, 新加坡, 2019-12-14
Authors:  Fan ZY(范志赟);  Li J(李杰);  Zhou SY(周世玉);  Xu B(徐波)
Adobe PDF(361Kb)  |  Favorite  |  View/Download:19/7  |  Submit date:2022/09/17
Speech-Transformer, speaker adaptation, end-to-end speech recognition, speaker aware training, i-vector