Keynote Speakers

Keynote Speaker 1

Prof Hideki Kawahara, Emeritus Professor
Center for Innovative Research and Liaison, Wakayama University


Making speech tangible for a better understanding of human speech communication


This talk presents the underlying concepts, technologies, applications and future of STRAIGHT, a framework for speech analysis, modification and resynthesis which was initially designed to facilitate speech perception research. Also introduced will be recent advances which may provide new opportunities in speech communication research. One concerns "Temporally variable multi-aspect morphing of arbitrarily many voices" and the other "SparkNG: Speech Production and Auditory perception Research Kernel: The Next Generation." The STRAIGHT and its applications are freely available to academics. The SparkNG package is open sourced. The future of STRAIGHT will start from the open source package, YANG vocoder.

Speech provides rich side information channels which modify/expand its linguistic contents. While the recent resurgence of machine learning technologies makes speech-based communication with smart machines practical and accessible, these rich side information channels are not well exploited. "Making speech tangible" by introducing tools which enable quantitative and precise as well as intuitive/direct manipulation of speech parameters will, I hope, lead to a better understanding of human speech communication.


Hideki Kawahara is a professor emeritus of Wakayama University Japan. He received Bachelor of Eng., Master of Eng. and Ph.D. in Electrical Engineering from Hokkaido University, Sapporo Japan, in 1972, 1974 and 1977 respectively. In 1977, he joined the Musashino Electrical Communications Laboratories (ECL) of Nippon Telegraph and Telephone public corporation (later NTT Basic Research Laboratories), Tokyo, Japan. In 1992, he joined Human Information Processing Research Laboratories of Advanced Telecommunication Research Institute International (HIP-ATR), Kyoto, Japan as a department head. In 1997, he joined Wakayama University, Japan as a full professor and started the "Auditory Brain project" as a PI of CREST research initiative by JST. He retired Wakayama University in 2015 and promoted to an emeritus professor. From 2015 to 2016, he joined Google UK as a visiting research scientist. He is currently a visiting researcher of Riken, Japan. He received the best paper award of 1998-1999 EURASIP on the underlying principle of STRAIGHT. He was a Distinguished Lecturer of APSIPA in 2015 and 2016. His research interests are signal processing base on auditory representations, speech perception models and interactive tools for research and education in speech science. Since his first encounter with computers in 1970, he has been and is a toolmaker for the others and himself.

Keynote Speaker 2

Dr Rafael E. Banchs, Scientist
Institute for Infocomm Research(I2R), Agency for Science, Technology and Research (A-STAR), Singapore.


Empirical Adventures of a Retrieval-based Chatbot


In this talk I will present a simple but powerful retrieval-based chat-oriented dialogue system and some of the past and current experimental work conducted with it. First, a brief description of the data collection supporting the system will be presented, followed by a complete description of the system operating principles and architecture. Additional strategies allowing for system adaptation and learning will also be described and discussed. Then, a comparative evaluation between the proposed system and a baseline system will be presented, along with some additional experimental work conducted with it. Finally, current research efforts on using chat-oriented dialogue for coping with errors in task-oriented dialogue will be discussed. 


Rafael E. Banchs currently works as Research Scientist and technical lead of the Dialogue Technology Lab at the Institute for Infocomm Research in Singapore. His main areas of research include Machine Translation, Information Retrieval and Dialogue Systems. He also holds an appointment as Adjunct Associate Professor at the School of Computer Science and Engineering at Nanyang Technological University. He has been author and co-author of over a hundred papers in international conferences and technical journals, and has served as program committee member and co-organizer of several international workshops and conferences. He received the Ph.D. in Electrical Engineering from the University of Texas at Austin in 1998, and was awarded a Ramon y Cajal fellowship from the Spanish Ministry of Education and Science from 2004 to 2009.

Organized by

Technically sponsored by


Supported by

apsipa stb

Copyright © 2017 Chinese and Oriental Languages Information Processing Society (COLIPS)