Public Lecture “Spoken Language Technology”

Informatics Science Group – STEI ITB, Monday, March 28, 2011, held a public lecture with the theme “Speech and Speaker Recognition Technology”. The public lecture was held in Room 7602 and the main speaker was Prof. Seiichi Nakagawa from Toyohashi University of Technology – Japan. This public lecture was attended by students participating in the IF3054 and IF4058 courses.

Prof. Seiichi Nakagawa explains about Signal Processing. Speaker recognition with model MFCC generally only pays attention to the power spectrum and ignores phase information that cannot be recognized by the human senses. By using phase information, which has been normalized, so that it has window-independent characteristics, the shape and period of the sound source wave can be recognized.

After the public lecture ended at 11:00 a.m., a seminar and discussion on "Natural Language Processing, Text Mining, and the Language Grid Project" followed. The keynote speaker was Prof. Toru Ishida from Kyoto University, Japan.