Spoken Language Processing Laboratory


Lab Name and Affiliation

Spoken Language Processing Laboratory

Toyohashi University of Technology, Tenpaku-cho, Toyohashi, 441-8580, Japan

Lab Director (or Principal Investigator)

Seiichi Nakagawa received Dr. of Eng. degree from Kyoto University in 1977. He joined the Faculty of Kyoto University, in 1976, as a Research Associate in the Department of Information Sciences. He moved to Toyohashi University of Technology in 1980, which was founded in 1977. From1980 to 1983, he was an Assistant Professor, and from 1983 to 1990 he was an Associate Professor. Since 1990 he has been a Professor in the Department of Information and Computer Sciences, Toyohashi University of Technology, Toyohashi. From 1985 to 1986, he was a Visiting Scientist in the Department of Computer Science, Carnegie-Mellon University, Pittsburgh, USA. He received the 1997/2001/2013 Paper Award from the IEICE and the 1988 JC Bose Memorial Award from the Institution of Electro. Telecomm. Engrs. He was the founder of the Special Interest Group of Spoken Language Processing (SLP) of the Information Processing Soceity of Japan in 1994. His major interests in research include automatic speech recognition/speech processing, natural language processing, human interface, and artificial intelligence. He is Fellows of IEICE and IPSJ.

Lab Introduction

What are we studying ?

1) Large Vocabulary Continuous Speech Recognition for Japanese, Mongolian and English: GMM-HMM, DNN-HMM, DNN-HCNF
2) Language Model: Topic Dependent LM, Written-to-Spoken Style Transformation
3) Distant Speech/Speaker Recognition and Distant Speech Dereverberation
4) Speaker Identification/Verification using Phase Information
5) Speech & Music Separation and Recognition by using VQ / NMF
6) Speech Privacy Protection: Speech removal, Named Entity Detection
7) Spoken Dialogue System: Chat-like Dialogue System with One User & Two Agents
8) Multi-Modal Interface: Pet-Robot
9) Spoken Document Retrieval by using N-gram Index
10) Spoken Document Summarization / Translation of Class Room Lecture
11) Music Processing: Singer Identification, Lyrics Recognition
12) English / Japanese Pronunciation Evaluation: Online Pronunciation / Intelligibility Evaluation

Lab Contact E-mail

nakagawa@tut.jp, kyama@tut.jp