A brief overview of speech and audio processing efforts at IOA

Thursday, 22 November 2012 at 10:00 in INF 328

Yonghong Yan, Key Lab of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Science , Beijing, China

 

Abstract:
This talk presents a brief overview of speech and audio processing efforts at the Key Lab of Speech Acoustics and Content Understanding in CAS (Chinese Academy of Sciences). CAS is a leading academic institution in China. The Key Lab of Speech Acoustics and Content Understanding is the largest speech lab in China. The research interests of our lab focus on speech recognition, speaker recognition, speech signal processing, audio coding, sound analysis and multimedia retrieval etc. Since it's founding in 2002, the lab has completed many important research achievements. In industry, our lab can supply the best speech products and resolve methods in China. Our productions cover several platforms (telecom), desktop platform and embedded platform (wireless terminal equipments, PDA, etc). The lab's speech recognition productions for telecom have been used for business in more than 20 provinces. The desktop production has been integrated by Intel Digital Home Desktop Computer as binding software and our embedded productions have been integrated in many mobile phones and PDAs of different manufacturers.

About the Speaker:
Prof. Yonghong Yan is the director of the Key Lab of Speech Acoustics and Content Understanding , Chinese Academy of Science (CAS). He received his B.S degree from the EE Department of Tsinghua University in 1985 in P.R. China, and obtained his PhD degree in Computer Science at the Oregon Graduate Institute (OGI) in 1995. He worked at OGI since 1995, first as Assistant Professor, then as the Associate Director of the Center for Spoken Language Understanding (1997), and was appointed as Associate Professor in 1998. In late 1998, he joined Intel. He was responsible for speech recognition group and system engineering group and was promoted to be director and principal engineer in 2000. He also served as the chief architect for human computer interface at Intel Microprocessor Research Labs and as the Chairman of Human Computer Interface Research Council during the period. In 2002, he joined Institute of Acoustics, Chinese Academy of Science (CAS) under the “Oversea Outstanding Scholar Program” and started Key Lab of Speech Acoustics and Content Understanding in CAS, where he is professor and lab director.