Research interests

• Integration of speech and language processing
• Spontaneous speech recognition/understanding
• Large-vocabulary continuous speech recognition system
• Japanese speech understanding system - SPOJUS-SYNO -
• Spoken language interface system

Publication

Papers

• Jun-ichi Takami, Atsuhiko Kai, and Shigeki Sagayama: ``A pairwise discriminant approach using artificial neural networks for continuous speech recognition'', The Journal of the Acoustical Society of Japan (E), Vol.13, No.6, pp.411--418, 1992.

• Seiichi Nakagawa and Atsuhiko Kai: ``Context-Free Grammar Driven, Frame Synchronous HMM-Based Continuous Speech Recognition Methods Using Word Spotting'', IEICE Trans., Vol.J76-D-II, No.7, pp.1329--1336, 1993.(in Japanese)

• Seiichi Nakagawa and Atsuhiko Kai: ``A Context-Free Grammar Driven, One Pass HMM-Based Continuous Speech Recognition Method'', IEICE Trans., Vol.J76-D-II, No.7, pp.1337--1345, 1993.(in Japanese)

• Seiichi Nakagawa and Atsuhiko Kai: ``A Context-Free Grammar-Driven, One-Pass HMM-Based Continuous Speech Recognition Method'', Systems and Computers in Japan, Vol.25, No.4, pp.92--102, 1994. (English version of the above paper)

• Atsuhiko Kai and Seiichi Nakagawa: ``Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System'', IEICE Trans. on Information and Systems, Vol.E78-D, No.6, pp.698--704, 1995.

• Atsuhiko Kai and Seiichi Nakagawa: ``Comparison of Continuous Speech Recognition Systems with Unknown Word Processing for Speech Disfluencies'', IEICE Trans., Vol.J80-D-II, No.10, pp.2615--2625, 1997.(in Japanese)

• Atsuhiko Kai and Seiichi Nakagawa: ``Comparison of Continuous Speech Recognition Systems with Unknown-Word Processing for Speech Disfluencies'', Systems and Computers in Japan, Vol.29, No.9, pp.43--53, 1998. (English version of the above paper)

• Seiichi Nakagawa, Miwako Torii, Atsuhiko Kai and Hirobumi Nakanishi: ``An Isolated Spoken Word Recognition System with Capability of Registration of New Words'', Trans. IEE Japan, Vol.118-C, No.6, pp.865--872, 1998.(in Japanese)

• Atsuhiko Kai, Yoshifumi Hirose and Seiichi Nakagawa: ``Dealing with Out-of-vocabulary Words and Filled Pauses in Word N-gram Based Speech Recognition System'', IPSJ Trans., Vol.40, No.4, pp.1383--1394, 1999.(in Japanese)

• Toshihiko Itoh, Atsuhiko Kai, Yoshiyuki Iwamoto, Makoto Mizutani, Hiroki Yuasa, Tatsuhiro Konishi and Yukihiro Itoh: ``Comparison of Linguistic and Acoustic Features Caused by Different Dialogue Situations in a Landmark-input Task'', IPSJ Journal, Vol.43, No.7, pp.2118--2129, 2002.(in Japanese)

• Shin-ichi Kawamoto, Hiroshi Shimodaira, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katsunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Atsuhiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro, and Shigeki Sagayama: ``Design of Software Toolkit for Anthropomorphic Spoken Dialog Agent Software with Customization-oriented Features'', IPSJ Journal, Vol.43, No.7, pp.2249--2263, 2002.(in Japanese)

• Atsuhiko Kai, Hirokazu Mori, Takahiro Nakano and Seiichi Nakagawa: ``Speech User Interface System for Form-based Web Information Retrieval Services and Its Usability Evaluation'', IPSJ Journal, Vol.46, No.5, pp.1318--1329, 2005.(in Japanese)

• N. Fujiwara, T. Itoh, K. Araki, A. Kai, T. Konishi, and Y. Itoh: ``Spoken Language Understanding Method Using Confidence Measure and Dialogue History'', IEICE Trans., Vol.J89-D, No.7, pp.1493--1503, 2006.(in Japanese)

• N. Fujiwara, T. Itoh, K. Araki, A. Kai, T. Konishi and Y. Itoh: ``Spoken Language Understanding Method Using Confidence Measure and Dialogue History'', Systems and Computers in Japan, Vol.38, No.9, pp.21--31, 2007. (English version of the above paper)

International Conference & Symposium

• Atsuhiko Kai and Seiichi Nakagawa: ``A Frame-Synchronous Continuous Speech Recognition Algorithm Using a Top-Down Parsing of Context-Free Grammar'', Proc. of International Conference on Spoken Language Processing (ICSLP 92), Alberta, Canada, pp.257--260, 1992.

• Atsuhiko Kai and Seiichi Nakagawa: ``Evaluation of Unknown Word Processing in a Spoken Word Recognition System'', Proc. of International Conference on Spoken Language Processing (ICSLP 94), Yokohama, Japan, pp.2151--2154, 1994.

• Atsuhiko Kai and Seiichi Nakagawa: ``Investigation on Unknown Word Processing and Strategies for Spontaneous Speech Understanding", Proc. of EUROSPEECH'95, Madrid, Spain, pp.2095--2098, 1995.

• Atsuhiko Kai and Seiichi Nakagawa: ``A Continuous Speech Recognition System Using Loosely Constrained Linguistic Knowledge for Spontaneous Speech'', Proc. of the first China-Japan Workshop on Spoken Language Processing (CJSLP'97), Huang Shan, P.R. China, pp.240--245, 1997.

• Seiichi Nakagawa, Atsuhiko Kai, Toshihiko Itoh and Masaki Ida: ``An Isolated/Continuous Speech Recognition System on a Personal Computer'', Proc. of the first China-Japan Workshop on Spoken Language Processing (CJSLP'97), Huang Shan, P.R. China, pp.216--223, 1997.

• Atsuhiko Kai and Seiichi Nakagawa: ``An acoustic look-ahead method for efficient frame-synchronous search in a large vocabulary speech recognition system'', Proc. of International Conference on Speech Processing (ICSP'97), Seoul, Korea, pp.513--518, 1997.

• Atsuhiko Kai, Yoshifumi Hirose and Seiichi Nakagawa: ``Dealing with out-of-vocabulary words and speech disfluencies in an N-gram based speech understanding system'', Proc. of International Conference on Spoken Language Processing (ICSLP 98), Sydney, Australia, pp.2427--2430, 1998.

• Atsuhiko Kai, Takahiro Nakano and Seiichi Nakagawa: ``A speech interface system for information retrieval tasks on the WWW'', Proc. of International Workshop Speech and Computer (SPECOM'99), Moscow, Russia, pp.141--144, 1999.

• Atsuhiko Kai, Takahiro Nakano and Seiichi Nakagawa: ``Usability of Browser-Based Pen-Touch/Speech User Interfaces for Form-Based Applications in Mobile Environment'', Lecture Notes in Computer Science 1948: Advances in Multimodal Interfaces - ICMI2000, pp.549--556, 2000.

• Atsuhiko Kai and Seiichi Nakagawa: ``Analysis of prosodic features on key-phrases and corrections in spoken dialogue'', Proc. for 2001 2nd Plenary Meeting and Symposium on Prosody and Speech Processing (Organized by Scientific Research of Priority Areas(B), Ministry of Science, Culture, Sports, Education, Japan), pp.179--184, 2002.

• Atsuhiko Kai, Yukari Nonomura, Toshihiko Itoh, Tatsuhiro Konishi and Yukihiro Itoh: ``Influence of different dialogue situations on user's behavior in spoken corrections'', Proc. of International Conference on Spoken Language Processing (ICSLP 2002), Denver, Colorado USA, pp.1189--1192, 2002.

• Toshihiko Itoh, Atsuhiko Kai, Tatsuhiro Konishi and Yukihiro Itoh: ``Linguistic and acoustic changes of user's utterances caused by different dialogue situations'', Proc. of International Conference on Spoken Language Processing (ICSLP 2002), Denver, Colorado USA, pp.545--548, 2002.

• Shin-ichi Kawamoto, Hiroshi Shimodaira, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katsunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Atsuhiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro, and Shigeki Sagayama: ``Open-source software for developing anthropomorphic spoken dialog agents'', In Proceedings of the International Workshop on LIFELIKE ANIMATED AGENTS: Tools, Affective Functions, and Applications, August 2002.

• Atsuhiko Kai and Toshihiko Itoh: ``Prosodic feature and its application for detecting spoken corrections'', Proc. for 2002 2nd Plenary Meeting and Symposium on Prosody and Speech Processing (Organized by Scientific Research of Priority Areas, Ministry of Education, Culture, Sports, Science and Technology, Japan), pp.115--120, 2003.

• Toshihiko Itoh, Atsuhiko Kai, Yukihiro Itoh and Tatsuhiro Konishi: ``An understanding strategy based on plausibility score in recognition history using CSR confidence measure'', Proc. of International Conference on Spoken Language Processing (INTERSPEECH 2004 - ICSLP), pp.2133--2136, 2004.

Books

• Y. Matsushita and T. Yashiro (Eds.), ``ITS and Information Communication Technology'', chap. 7.2, pp. 132-139, Shokabo, Tokyo, 2003.(in Japanese)

• Shin-ichi Kawamoto, Hiroshi Shimodaira, Tsuneo Nitta, Takuya Nishimoto, Satoshi Nakamura, Katsunobu Itou, Shigeo Morishima, Tatsuo Yotsukura, Atsuhiko Kai, Akinobu Lee, Yoichi Yamashita, Takao Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi Yamada, Yasuharu Den, Takehito Utsuro, Shigeki Sagayama, ``Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents,'' Life-Like Characters. Tools, Affective Functions, and Applications. Helmut Prendinger et al. (Eds.) Springer, pp.187-212, Nov 2003.

• S. Nakagawa, A. Kai and T. Itoh, ``The Spoken Dialogue System of TUT'' in S. Nakagawa, M. Okada and T. Kawahara (Eds.), Spoken Language Systems, pp.129-142, Ohmsha/IOS Press, 2005.

Doctor's thesis

Atsuhiko Kai: ``A Study on Speech Recognition System for Spontaneous Speech," D. Thesis, Toyohashi University of Technology (1996.1)
Abstract of D. Thesis

Back to My Top Page