ASR:2015-04-27

Speech Processing

AM development

Environment

• To update the wiki enviroment infomation --done

RNN AM

• hold -- Chao Liu
• details at http://liuc.cslt.org/pages/rnnam.html
• Test monophone on RNN using dark-knowledge
• run using wsj,MPE

Mic-Array

• Change the prediction from fbank to spectrum features
• investigate alpha parameter in time domian and frquency domain
• ALPHA>=0, using data generated by reverber toolkit
• consider theta
• make spectrom feature with Kaldi

RNN-DAE(Deep based Auto-Encode-RNN)

• HOLD --Zhiyong Zhang
• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

Speaker ID

• DNN-based sid --Yiye Lin
• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

Ivector&Dvector based ASR

• Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric -- Tian Lan
• Direct using the dark-knowledge strategy to do the ivector training -- Tian Lan
• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340

Dark knowledge

• Ensemble --Zhiyong Zhang

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang

• adaptation for chinglish under investigation --Mengyuan Zhao
• chinglish adaptation task best performane is obtained ofrom retraining , dark knowledge helps adapt model,try to tune papameters layear by layer ,change cv --Mengyuan Zhao
• unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng

• test large database with AMIDA

bilingual recognition

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang