Chihaya's sketch of Gitchang Sato's photo of Gitchang

Hiroshi "Gitchang" Okuno

It taught me a lot about life, that it doesn't always go your way and you have to find happiness in everything you do. Stand tall, hold your hand up high and keep on fighting. I think that's what the Olympics are all about.

Michelle Kwan, reflecting on winning sliver instead of gold
Nagano, Feb. 22, 1998.
Japanese page .
Dr. Hiroshi G. Okuno was appointed the professor of Speech Media Laboratory, Department of Intelligence Science and Technology, Gradulate School of Informatics, Kyoto Universiton on April 1, 2001.

o Contents

o Research Areas

NUE NUE (New Unified Environment) Research Project

o Recent Publications -- Papers and Articles

  1. Hiroshi G. Okuno, Kazuhiro Nakadai, Ken'ichi Hidai, Hiroshi Mizoguchi, Hiroaki Kitano: Human-Robot Non-Verbal Interaction Empowered by Real-Time Auditory and Visual Multiple-Talker Tracking Advanced Robotics, in print, Robotics Society of Japan, 2002.

  2. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Real-Time Auditory and Visual Multiple-Speaker Tracking For Human-Robot Interaction. Journal of Robotics and Mechatronics, special issue on Human Robot Interaction, in print, Mechatronics Society of Japan, 2002.

  3. Kentaro Umesawa, Takamichi Saito, Hiroshi G. Okuno: A Privacy-enhanced SSL Access Control with Authorization Certificates. IPSJ Journal, Vol.43, No.8 (Aug. 2002) pp.2562--2572. Paper in html

  4. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Auditory Fovea Based Speech Separation and Its Application to Dialog System. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2002), accepted, IEEE, Geneva, Oct. 2002.

  5. Yoko Yamakata, Tatsuya Kawahara, Hiroshi G. Okuno: BELIEF NETWORK BASED DISAMBIGUATION OF OBJECT REFERENCE IN SPOKEN DIALOGUE SYSTEM FOR ROBOT. Proceedings of 2002 International Conference on Spoken Language Processing (ICSLP-2002), 170-176, ASA, ASJ, and ESCA, Denver, Sep. 2002.

  6. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: AUDITORY FOVEA BASED SPEECH ENCHANCEMENT AND ITS APPLICATION TO HUMAN-ROBOT DIALOG SYSTEM. Proceedings of 2002 International Conference on Spoken Language Processing (ICSLP-2002), 1817-1820, ASA, ASJ, and ESCA, Denver, Sep. 2002.

  7. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: REAL-TIME SOUND SOURCE LOCALIZATION AND SEPARATION FOR ROBOT AUDITION. Proceedings of 2002 International Conference on Spoken Language Processing (ICSLP-2002), 193-196, ASA, ASJ, and ESCA, Denver, Sep. 2002. Paper in PDF

  8. Kazunori Komatani, Tatsuya Kawahara, Ryosuke Ito, Hiroshi G. Okuno: Efficient Dialogue Strategy to Find Users' Intended Items from Information Query Results, Proceedings of the Nineteenth International Conference on Computational Linguistics (Coling-2002), accepted, Aug. 2002.

  9. Hiroshi G. Okuno, Kazuhiro Nakadai, Hiroaki Kitano: Realizing Audio-Visually triggered ELIZA-like non-verbal Behaviors. In Ishizuka, M. and Slaney, J. (eds) PRICAI 2002: Trends in Artificial Intelligence (Seventh Pacific Rim International Conference on Artificial Intelligence), Lecture Notes in Artificial Intelligence 2417, pp.552--562 Springer-Verlag, Tokyo, Aug. 2002. Paper in PDF

  10. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Exploiting Auditory Fovea in Humanoid-Human Interaction. Proceedings of Eighteenth National Conference on Artificial Intelligence (AAAI-2002), 431-438, AAAI, Edmonton, Aug. 2002. Paper in PDF

  11. Hiroshi G. Okuno, Kazuhiro Nakadai, Hiroaki Kitano: Non-Verbal Eliza-like Human Behaviors in Human-Robot Interaction through Real-Time Auditory and Visual Multiple-Talker Tracking. Proceedings of the Third International Workshop on Cognitive Robotics (CogRob-2002), pp.59--65, Technical Report WS-02-05, AAAI Press, Edmonton, Jul. 2002. Paper in PDF

  12. Hiroshi G. Okuno, Kazuhiro Nakadai, Hiroaki Kitano: Social Interaction of Humanoid Robot through Auditory and Visual Tracking. In Hendtlass, T., and Ali, M. (Eds.) Developments in Applied Artificial Intelligence, Proceedings of Eighteenth International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE-2002), Cairns, Australia, June 2002, Lecture Notes in Artificial Intelligence 2358, pp.725-735, Springer-Verlag. Paper in PDF

  13. Yoko Yamakata, Tatsuya Kawahara, Hiroshi G. Okuno: Belief Network based Disambiguation of Word Reference in Spoken Dialogue System for Robot. Proceedings of ISCA Tutorial and Research Workshop on Multi-Modal Dialogue in Mobile Environments, Germany, Jun. 2002.

  14. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Real-Time Speaker Localization and Speech Separation by Audio-Visual Integration. Proceedings of IEEE/RSJ International Conference on Robots and Automation (ICRA-2002), 1043-1049, IEEE, May 2002. Paper in PDF

  15. Hiroshi G. Okuno, Kazuhiro Nakadai, Lourens, T., Hiroaki Kitano: Sound and Visual Tracking by Active Audition, Q. Jin, J. Li, N. Zhang, J. Cheng, C.Yu, S. Noguchi (Eds.) Enabling Society with Information Technology, pp.174-185, Springer-Verlag, Tokyo, Jan. 2002.

  16. Takamichi Saito, Kentaro Umesawa, Hiroshi G. Okuno: プライバシーを重視するアクセス制御システムの一方式. Transaction of IEICE, Vol.D1, IEICE, Dec. 2001.

    Kazuhiro Nakadai, Ken'ichi Hidai, Hiroshi G. Okuno, Hiroaki Kitano: Real-Time Active Human Tracking by Hierarchical Integration of Audition and Vision. Proceedings of IEEE-RAS International Conference on Humanoid Robots (Humanoids2001), pp.91-98, IEEE, Nov. 2001. Paper in PDF

  17. Kazuhiro Nakadai, Tatsuya Matsui, Hiroshi G. Okuno, Hiroaki Kitano: Epipolar Geometry Based Sound Localization and Extraction for Humanoid Audition. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2001), IEEE, Maui, Hawaii, Oct. 2001. Paper in PDF

  18. Hiroshi G. Okuno, Kazuhiro Nakadai, T. Lourens, Hiroaki Kitano: Human-Robot Interaction Through Real-Time Auditory and Visual Multiple-Talker Tracking Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2001), IEEE, Maui, Hawaii, Oct. 2001. Paper in PDF Finalist of Best Paper Award (Aug. 2002)

  19. Lourens, T., Hiroshi G. Okuno, Hiroaki Kitano: Automatic Graph Extraction from Color Images. Proceedings of the 11th International Conference on Image Analysis and Processing (ICIAP 2001), pp.302--308, Palermo, Italy, Sep. 2001,

  20. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Real-Time Multiple Speaker Tracking by Multi-Modal Integration for Mobile Robots. Proceedings of European Conforence on Speech Processing (Eurospeech 2001), pp.1193-1196, Aalborg, Denmark, Sep. 2001. Paper in PDF

  21. Hiroshi G. Okuno, Kazuhiro Nakadai, T. Lourens, Hiroaki Kitano: Separating Three Simultaneous Speeches with Two Microphones by Integrating Auditory and Visual Processing. Proceedings of European Conforence on Speech Processing (Eurospeech 2001), pp.2643-2646, Aalborg, Denmark, Sep. 2001. Paper in PDF

  22. Kentaro Umesawa, Takamichi Saito, Hiroshi G. Okuno: プライバシーを重視したアクセス制御機構の提案. IPSJ Journal, Vol.42, No.8 (Aug. 2001) pp.2067-2076. Paper in html

  23. Kazuhiro Nakadai, Ken-ichi Hidai, Hiroshi Mizoguchi, Hiroshi G. Okuno, Hiroaki Kitano: Real-Time Auditory and Visual Multiple-Object Tracking for Robots. Proc. of 17th International Joint Conference on Artificial Intelligence (IJCAI-01), pp.1425-1432, Seattle, Aug. 2001. Paper in PDF

  24. Lourens, T., Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Detection of Oriented Repetitive Alternating Patterns in Color Images --- A Computational Model of Monkey Grating Cells. Proc. of Sixth International Work-Conference on Artificial and Natural Neural Networks (IWANN2001), Lecture Notes in Artificial Intelligence, No.2084, 95-107, Springer-Verlag. Granada, Spain, June 2001.

  25. Hiroshi G. Okuno, Kazuhiro Nakadai, Lourens, T., Hiroaki Kitano: Sound and Visual Tracking for Humanoid Robot, Proc. of 17th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE-2001) , Lecture Notes in Artificial Intelligence, No.2070, 640-650, Springer-Verlag. Budapest, Hungary, June 2001. Best Paper Award (1st Prize) Paper in PDF

  26. Frank, I., Kumiko Ishii-Tanaka, Hiroshi G. Okuno, Junichi Akita, Yukiko Nakagawa, K. Maeda, Kazuhiro Nakadai, Hiroaki Kitano: And The Fans are Going Wild! SIG plus MIKE. RoboCup 2000: Robot Soccer World Cup IV, Lecture Notes in Artificial Intelligence No.2019, 139-148, Springer-Verlag, May 2001.

  27. Yukiko Nakagawa, Hiroshi G. Okuno, Hiroaki Kitano: Bridging gap between small sized league and simulator league. RoboCup 2000: Robot Soccer World Cup IV, Lecture Notes in Artificial Intelligence No.2019, 209-218, Springer-Verlag, May 2001.

  28. Hiroaki Kitano: Hiroshi G. Okuno, Mineo Morohashi, Koji Kyoda, Kazuhiro Nakadai (Translation): "How to Build a PC Cluster - Linux cluster Beowulf", Sangyo-Tosho, March, 2001.

  29. Kazuhiro Nakadai, Ken-ichi Hidai, Hiroshi Mizoguchi, Hiroshi G. Okuno, Hiroaki Kitano: Real-time Multiple Person Tracking by Face Recognition and Active Audition. SIG-Challenge-01-5, pp.27-34, JSAI, Mar. 2001.

  30. Hiroshi G. Okuno, Kazuhiro Nakadai, Lourens, T., Hiroaki Kitano: Sound and Visual Tracking for Humanoid, Proc. of 2000 International Conference on Information Society in the 21st Century: Emerging Technologies and New Challenges (IS2000) , 254--261, Aizu-Wakamatsu, Nov. 2000. Best Paper Award

  31. Kazuhiro Nakadai, Tatsuya Matsui, Hiroshi G. Okuno, Hiroaki Kitano: Active Audition System and Humanoid Exterior Design. Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2000), 1453--1461, Takamatsu, Nov. 2000. Paper in PDF

  32. Hiroaki Kitano, Hiroshi G. Okuno, Kazuhiro Nakadai, Theo Sabische, Tatsuya Matsui, Design and Architecture of SIG the Humanoid: An Experiemntal Platformfor Integratind Perception in RoboCup Humanoid Challenge. Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2000), 181--190, Takamatsu, Nov. 2000.

  33. Iris Fermin, Hiroshi Ishiguro, Hiroshi G. Okuno, Hiroaki Kitano: A Framework for Integrating Sensory Information in a Humanoid Robot. Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2000), 1748--1753, Takamatsu, Nov. 2000.

  34. Hiroshi G. Okuno: Computational Auditory Scene Analysis --- Toward the Recognition of a Mixture of Sounds", Joho Shori, 1096--1101, IPSJ, Oct. 2000.

  35. Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano. Humanoid Active Audition System. Proc. of First IEEE-RAS International Conference on Humanoid Robots (Humanoids2000), Cambridge, Sep. 2000. Paper in PDF

  36. Lourens, T., Kazuhiro Nakadai, Hiroshi G. Okuno, Hiroaki Kitano: Selective Attention by Integration of Vision and Audition. Proc. of First IEEE-RAS International Conference on Humanoid Robots (Humanoids2000), Cambridge, Sep. 2000.

  37. Kazuhiro Nakadai, Lourens, T., Hiroshi G. Okuno, Hiroaki Kitano: Humanoid Active Audition System Improved by The Cover Acoustics. In Mizoguchi, R. and Slaney, J. (eds) PRICAI 2000 Topics in Artificial Intelligence (Sixth Pacific Rim International Conference on Artificial Intelligence), 544--554, Springer Lecture Notes in Artificial Intelligence No. 1886, Melborne, Aug. 2000. Paper in PDF

  38. Frank, I., Kumiko Ishii-Tanaka, Hiroshi G. Okuno, Kazuhiro Nakadai, Yukiko Nakagawa, K. Maeda, Hiroaki Kitano: And The Fans are Going Wild! SIG plus MIKE. Proc. of the Fourth Workshop on RoboCup (RoboCup-2000), 267--276, RoboCup, Melbourne, Aug. 2000.

  39. Yukiko Nakagawa, Hiroshi G. Okuno, Hiroaki Kitano: Bridging gap between small sized league and simulator league. Proc. of the Fourth Workshop on RoboCup (RoboCup-2000), 1--10, RoboCup, Melbourne, Aug. 2000.

  40. Kazuhiro Nakadai, Lourens, T., Hiroshi G. Okuno, Hiroaki Kitano: Active Audition for Humanoid. Proc. of the Seventeenth National Conference on Artificial Intelligence (AAAI-2000), 832-839, Austin, Aug. 2000. Paper in PDF

  41. Hiroshi G. Okuno, Koji Kyoda, Mineo Morohashi, Hiroaki Kitano: Initial Assessment of ERATO-1 Beowulf-Class Cluster. Ito, T. and Yuasa, T. (eds.) Parallel and Distributed Computing in Symbolic and Irregular Applications, World Scientific Publishing, 372-383, 2000.
  42. Tomohiro Nakatani, Hiroshi G. Okuno: "Sound ontology based integration of Computational Auditory Scene Analysis Systems", Journal of Japanese Society for Artificial Intelligence, Vol.14, No.6 (Dec. 1999) (in press).

  43. Hiroshi G. Okuno, Yukiko Nakagawa Hiroaki Kitano: "Integrating Auditory and Visual Perception for Robotic Soccer Players". Proc. of International Conference on Systems, Man, and Cybernetics (SMC-99), Vol.VI, 744-749, IEEE, Tokyo, Oct. 1999. Paper in PDF

  44. Hiroshi G. Okuno, Shiro Ikeda, Tomohiro Nakatani: "Combining Independent Component Analysis and Sound Stream Segregation". Proc. of IJCAI-99 Workshop on Computational Auditory Scene Analysis (CASA'99), IJCAI, pp.92--98, Stockholm, Sweden, Aug. 1999. Paper in postscript

  45. Hiroshi G. Okuno, Yukiko Nakagawa Hiroaki Kitano: "Incorporating Visual Information into Sound Source Separation". Proc. of IJCAI-99 Workshop on Computational Auditory Scene Analysis (CASA'99), IJCAI, pp.99--107, Stockholm, Sweden, Aug. 1999. Paper in postscript

  46. Yukiko Nakagawa, Hiroshi G. Okuno, Hiroaki Kitano: "Using Vision to Improve Sound Source Separation", Proc. of the 16th National Conference on Artificial Intelligence (AAAI-99), pp.768--775, AAAI, Orlando, Jul. 1999. Paper in postscript, in PDF

  47. Hiroshi G. Okuno, Koji M. Kyoda, Mineo Morohashi, Hiroaki Kitano: "Initial Assessment of ERATO-1 Beowulf-class Cluster" Proc. of International Symposium on Parallel and Distributed Processing for Symbolic and Irregular Applications", Sendai, July, 1999.

  48. Hiroshi G. Okuno, Tomohiro Nakatani, Takeshi Kawabata: "Listening to Two Simultaneous Speeches", Speech Communcations, Vol.27, Nos.3-4 (Apr. 1999), pp.299-310, Elsevier, 1999.

  49. Tomohiro Nakatani, Hiroshi G. Okuno: "Harmonic Sound Stream Segregation Using Localization and Its Application to Speech Stream Segregation", Speech Communcations, Vol.27, Nos.3-4 (Apr. 1999), pp.209-222, Elsevier, 1999.

  50. Hiroshi G. Okuno, Shin'ichi Minato, and Hideki Isozaki, "On the Properties of Combination Set Operations", Information Processing Letters, Elsevier, Vol. 66, No.4 (May 1998) pp.195-199. Preprint in postscript

  51. Tomohiro Nakatani, Hiroshi G. Okuno: "Sound Ontology for Computational Auditory Scene Analysis", Proc. of the 15th National Conference on Artificial Intelligence (AAAI-98), Vol.1, pp.30-35, Madison, Jul. 1998. Paper in postscript

  52. Takahide Hoshide, Masayoshi Nose, Hisazumi Tsuchida, Kisaku Fujimoto, and Hiroshi G. Okuno: "Adaptive realtime planning for multi-media communication services by multi-agent system", Transaction of Institute of Electronics, Information and Communication Engineers, B-I Vol.J81, No.7 (July 1998) pp.440-449.

  53. Osamu Akashi, Ken'ichiro Murakami, Yoshiji Amagai, and Hiroshi G. Okuno: "NueLinda Model and Its implementation by self-description", Computer Software, Japanese Society for Software Science and Technology, Iwanami Publisher, Vol.14, No.1 (Jan. 1998) pp.24-33.

  54. Hiroshi G. Okuno: "Invitation to Computational Auditory Scene Analysis Research", Journal of Japanese Society for Artificial Intelligence, Vol.13, No.1 (Jan. 1998) pp.45-46.

  55. Hiroshi G. Okuno, Katashi Nagao, Yoshiyuki Koseki, Hiroshi Yasuhara, and Ken'ichi Yoshida: "Stand-alone and Open-ended Collection of Papers with Retrieval Capability --- Experience with JSAI 10th Anniversary Commemorative CD-ROM ---" Journal of Japanese Society for Artificial Intelligence, Vol.12, No.6 (Nov. 1997) pp.911-920.

  56. Takahide Hoshide, Masayoshi Nose, Hisazumi Tsuchida, and Hiroshi G. Okuno: "Adaptive and real-time planning architecture in IDSP system", NTT R & D, Vol.46, No.11 (Nov. 1997) pp.1257-1264.

  57. Hiroshi G. Okuno, Tomohiro Nakatani, and Takeshi Kawabata: "Challenge Problem: Understanding Three Simultaneous Speakers", Proc. of the 15th International Joint Conference on Artificial Intelligence (IJCAI-97), Vol.1, pp.30-35, IJCAI, Nagoya, Aug. 1997.

  58. Hiroshi G. Okuno, and Tomohiro Nakatani: "Sound Stream Segregation by Multiagent System", System/Infomation/Control, Journal of the Institute of Systems, Control and Information Engineers, Vol.41, No.8 (Aug. 1997) pp.309-315.

  59. Hiroshi G. Okuno, Tomohiro Nakatani, and Takeshi Kawabata: "Speech Stream Segregation and Preliminary Results on Listening to Several Speeches Simultaneously", Transaction of Information Processing Society of Japan, Vol.38, No.3 (Mar. 1997) pp.510-523.

  60. Tomohiro Nakatani, Masataka Goto, Takeshi Kawabata, and Hiroshi G. Okuno: "Proposal of Residue-Driven Architectureand Its application to for Sound Stream Segregation", Journal of Japanese Society for Artificial Intelligence, Vol.12, No.1 (Jan. 1997) pp.111-120.

  61. Hiroto Masaki, Itsuro Saito, Mitsuru Ishizuka, and Hiroshi G. Okuno: "Efficient Understanding of Three Orthographic Views Using Binary Decision Diagram", Transaction of Information Processing Society of Japan, Vol.37, No.11 (Nov. 1996) pp.1969-1979.

  62. Hiroshi G. Okuno, Tomohiro Nakatani, and Takeshi Kawabata: A New Speech Enhancement : Speech Stream Segregation. Proceedings of 1996 International Conference on Spoken Langugage Processing (ICSLP 96), Vol.4, pp.2356-2359, ASA, IEEE, JSAS, Philadelphia, U.S.A., Oct. 1996. Abstract, Paper in postscript

  63. Hiroshi G. Okuno, Tomohiro Nakatani, and Takeshi Kawabata: Interfacing Sound Stream Segregation to Speech Recognition Systems --- Preliminary Results of Listening to Several Things at the Same Time. Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), to appear, Portland, U.S.A., Aug. 1996. Abstract, Paper in postscript

  64. Hiroshi G. Okuno, Osamu Shimokuni, and Hidehiko Tanaka: "Design and Implementation of Multiple-context Truth Maintenance System with Binary Decision Diagram." Proceedings of the Ninth International Conference on Industirial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE-96), to appear, ISAI, Fukuoka, Japan, Jun. 1996. Abstract. Paper in postscript

  65. Tomohiro Nakatani, Masataka Goto, and Hiroshi G. Okuno: "Localization by harmonic structure and its application to harmonic sound stream segregation." Proceedings of 1996 International Conference on Acoustics, Speech and Signal Processing (ICASSP-96), Vol II:653--656, IEEE, Atlanta, U.S.A., May 1996.

  66. Hiroshi G. Okuno, Osamu Shimokuni, and Hidehiko Tanaka: "Binary Decision Diagram based Multipli-Context type Truth Maintenance System BMTMS", Journal of Japanese Association for Artificial Intelligence, , Vol.11, No.3 (Mar. 1996) pp.280-289. Abstract.

o Recent Publications -- Books

o Activities in Academia

JSSST Logo Japanese Society for Software Science and Technology Councillor (Planning Chair)
JSAI Logo Japanese Association for Artificial Intelligence, Special Interest Group on Artificial Intelligence Challenges (former SIG on Parallel Processing and Hot Topics for Artificial Intelligence).

Seventh International Conference on Information and Knowledge Management (CIKM '98) Publicity Co-chair
IJCAI-97 Logo IJCAI-97 in Nagoya Publicity Chair
CASA Logo
NUE Logo NUE (New Unified Environment) Research Project Home Page
NTT LogoNTT Home Page
Stanford University Computer Sciene Department Knowledge Systems Lab.
Department of Electonic Engineering , Faculty of Engineering, The University of Tokyo.
Symbio logo Kitano Symbiotic Systems Project, ERATO logo ERATO, JST logo Japan Science and Technology Corporation.
Information Processing Society of Japan,
Japanese Association for Artificial Intelligence,
Japanese Society of Cognitive Science,,
Japan Society for Software Science and Technology (member of trustee),
ACM,
AAAI
IJCAI-97 Nagoya
IEEE P610 Computer Dictionary Project
JSAI 10th anniversary CD-ROM publication Committee
IJCAI-99 Workshop on Computational Auditory Scene Analysis
IJCAI-97 Workshop on Computational Auditory Scene Analysis
IJCAI-95 Workshop on Computational Auditory Scene Analysis

Last update: Sun Sep 1 18:15:57 2002