Graduate School of Science and Engineering, and Information Technology Center, Saitama University, Japan

Biography: Tetsuya Shimamura is a Professor of Graduate School of Science and Engineering, and Information Technology Center at Saitama University in Japan. He was Dean of Information Technology Center at Saitama University in 2014 and 2015. In 1995 and 1996, he joined Loughborough University, UK, and The Queen's University of Belfast, UK, respectively, as a visiting Professor. His research interests are in digital signal processing and its applications to speech, audio, image and communication systems. He has published over 90 refereed journal articles and 220 international conference proceedings papers. He is an author or co-author of eight books, and a member of the organizing committee of several international conferences. He has received IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, Gold Paper Award, in 2012, WSEAS International Conference on Multimedia Systems and Signal Processing, Best Paper Award, in 2013, and IEEE IFOST, Best Paper Award, in 2014. Also, he is a recipient of Journal of Signal Processing, Best Paper Award, in 2013, 2015, and 2016.

Speech Title: Spectral Analysis for Bone-Conducted Speech

Abstract: Recently, a lot of attentions have been paid to bone-conducted speech due to its robustness against noise. To accomplish acceptable performances of speech recognition /speaker recognition even in highly noisy environments where we stay every day, the use of bone-conducted speech would be promised. However, analysis techniques for bone-conducted speech are not clear up to now, because it is different from normal speech. In this talk, a spectral analysis technique which was developed recently is explained in a comparative fashion with the corresponding standard technique used for normal speech, and some demonstrations are shown. It will be expected for the audience to realize how effective bone-conducted speech is in future speech processing.

Keywords: bone conduction, noisy environments, speech recognition, speaker recognition