确定 取消 应用
对外交流

关于微软亚洲研究院宋歌平博士学术报告的通知

发布日期 :2007-10-18    阅读次数 :4788

报告题目: Hidden Markov Model (HMM) for Speech Recognition and Synthesis

时间:20071026日下午15:30-17:30

地点:教三信息学院440会议室

报告人简介

Frank Soong is currently a Principal Researcher and Manager of the Speech Research Group at Microsoft Research Asia (MSRA), Beijing, China. His Speech Group works on fundamental research and practical applications, including: automatic speech recognition (ASR), text-to-speech synthesis (TTS) and audio information management and extraction (AIME).

He spent more than 25 years in speech research at world-renowned organizations such as Bell Labs USA and ATR Japan. At Bell Labs, he led an award-winning team to transfer research technologies to voice-activated dialing mobile phone product which has been rated by the Mobile Office Magazine as the “outstandingly the best”. He was a co-recipient of the Bell Labs President Gold Award for developing the Bell Labs Automatic Speech Recognition (BLASR) software package.

He is an elected member of the Speech and Language Technical Committee, IEEE Signal Processing Society, and served as an Associate Editor of the Speech and Audio Transactions. He published more than 150 papers, and co-edited the widely used reference book, Automatic Speech and Speech Recognition- Advanced Topics, Kluwer, 1996. He is the co-Director of the MSRA-CUHK Joint Research Lab and a visiting professor of the Chinese University of Hong Kong (CUHK) and a few other top-rated universities in China.

                                                                                                     信电系

信息与通信工程研究所

2007-10-18