大阳城国际娱乐官网信息技术研究院学术讲座

Speech Enhancement and Segregation based on Human Auditory Mechanisms

Professor Masato Akagi

School of Information Science, JAIST, Japan

时间: 2004年9月20日（星期一）上午9:00-10:00

地点: 大阳城国际娱乐官网信息科学技术大楼1-315室

ABSTARCT

Humans can perceive specific desired sounds without difficulty, even in noisy environments. This is a useful ability that many animals possess, and is referred to as the 'Cocktail party effect'. We believe that by modeling this mechanism we will be able to produce tools for speech enhancement and segregation, or for other problems in speech recognition and analysis. To construct models that mimic human sound perception ability, engineering know-how and knowledge of auditory physiology and/or psychoacoustics are required. This talk, first, introduces the basic concepts used to construct models such as “cancellation on the neural system” and “auditory scene analysis.” It then proposes models based on these concepts. Specifically, this talk discusses the following models and associated simulated results; speech enhancement through spatial filtering and an auditory sound segregation model based on auditory scene analysis.

ABOUT THE SPEAKER

Masato Akagi received the B.E. degree in Electronic Engineering from Nagoya Institute of Technology in 1979, the M.E. and the Dr. Eng. degrees in Computer Science from Tokyo Institute of Technology in 1981 and 1984, respectively. In 1984, he joined the Electrical Communication Laboratories, Nippon Telegraph and Telephone Corporation (NTT). From 1986 to 1990, he worked at the ATR Auditory and Visual Perception Research Laboratories. Since 1992, he has been with the School of Information Science, JAIST, where he is currently a professor. His research interests include Speech Perception Mechanisms of Humans, and Speech Signal Processing. Dr. Akagi received the IEICE Excellent Paper Award from the IEICE in 1987, and the Sato Prize for Outstanding Paper from the ASJ in 1998.

欢迎参加！

关于本讲座的任何事宜，请与郑方教授联系

（电话：138-0101-2234）