About Me

My name is Binbin Zhang (张彬彬). I was advised by Prof. Lei Xie at NWPU. my research interests include speech and corresponding applications, especially for speech recognition.

I'm the creator of wenet-e2e which is an open source community, WeNet which is a popular, production first and production ready end-to-end speech recognition toolkit, and WenetSpeech which is a 10000+ hours open source multi-domain chinese corpus for speech recognition.

I'm one of the designers and teachers of the open course "语音识别:从入门到精通"(Automatic Speech Recognition), I'm responsible for the GMM-HMM, DNN-HMM, discriminative training and LF-MMI parts of the course.

Please visit my Zhihu to follow my other work.

Education

M.S. in Computer Science and Technology
Northwestern Polytechnical University, 2014 to 2017.

B.E. in Computer Science and Technology
Northwestern Polytechnical University, 2010 to 2014.

Work Experiences

Speech Tech Lead @ Mobvoi
Focusing on speech tech and products, end-to-end speech recognition, 2018.08 to now

Speech Scientist @ Microsoft
Focusing on acoustic modeling, 2017.04 to 2018.08

Speech Intern @ Horizon Robotics
Focusing on acoustic modeling, 2016

Speech Intern @ Baidu Inc
Focusing on acoustic modeling, 2015

Publications

Please visit my Google Scholar profile.