TU Berlin

Quality and Usability Lab2012_05_12_Liao

Inhalt des Dokuments

zur Navigation

Some Aspects of Speech Signal Processing

Please notice exceptional date, time and place!

Location: Ernst-Reuter-Platz 7, 17th Floor, Room Sputnik

TITLE: Some Aspects of Speech Signal Processing – from microphone array integration, acoustic model decomposition to prosody-assisted ASR and speech coding.

SPEAKER: Yuan-Fu Liao

In this talk, I will first introduce our speech signal processing research group at National Taipei University and Chiao Tung University, Taiwan. Some of our aspects of speech signal processing and recent works will then be briefly summarized including (1) minimum error rate and confidence measure-based microphone array and speech recognizer integration, (2) joint factor analysis-based acoustic model decomposition for robust speech recognition and (3) a new prosodic modeling method and its applications to automatic speech recognition and speech coding.

Yuan-Fu Liao received the B.S., M.S., and Ph.D. degrees from National Chiao Tung University (NCTU), Hsinchu, Taiwan, R.O.C., in 1991, 1993, and 1998, respectively.
From January 1999 to June 1999, he was a Postdoctoral Researcher with the Department of Communication Engineering, National Chiao-Tung University, Taiwan. From September 1999 to February 2002, he become a Research Engineer with Philips Research East Asia, Taiwan. Since February 2002, he has been with the Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan, where he is currently a associate Professor. His current research interests are speech/speaker/language recognition, speech synthesis and computer-assisted  language learning.



Schnellnavigation zur Seite über Nummerneingabe