Biography
Chng Eng Siong graduated with a BEng (Hons) degree and a PhD degree from Department of Electrical and Electronics Engineering, University of Edinburgh in 1991 and 1996 respectively. After graduating, Dr Chng worked briefly in RIKEN (http://www.brain.riken.jp/ Japan) as a post-doctoral research staff before joining Institute of System Science (ISS) (Singapore) from 1996-1999.  In ISS, he was active in the area of online handwriting recognition and speech recognition systems with the Apple-ISS team.  He subsequently joined Lernout and Hauspie (1999-2001) and continued working in speech research. From 2001-2002, he joined Knowles Electronics (www.knowles.com) as Research Manager for microphone array. He joined Nanyang Technological University as assistant professor in 2003. He is currently supervising five PhD students and one MEng student working in speech and video processing related activities. His interests are: pattern recognition, DSP, speech enhancement and speech processing.

Abstract
This talk describes the I2R/NTU system submitted for the NIST Rich Transcription 2007 (RT-07) Meeting Recognition evaluation Multiple Distant Microphone (MDM) task. In our system, speaker turn detection and clustering is done using Direction of Arrival (DOA) in-formation. Purification of the resultant speaker clusters is then done by performing GMM modeling on acoustic features. As a final step, non- speech & silence removal is done. Our system achieved a competitive overall DER of 15.32% for the NIST Rich Transcription 2007 evaluation task.

附件