A robot referee for rock-paper-scissors sound games

Kazuhiro Nakadai, Shunichi Yamamoto, Hiroshi G. Okuno, Hirofumi Nakajima, Yuji Hasegawa, Hiroshi Tsujino

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Citations (Scopus)

Abstract

This paper describes a robot referee for "rockpaper-scissors (RPS)" sound games; the robot decides the winner from a combination of rock, paper and scissors uttered by two or three people simultaneously without using any visual information. In this referee task, the robot has to cope with speech with low signal-to-noise ratio (SNR) due to a mixture of speeches, robot motor noises, and ambient noises. Our robot referee system, thus, consists of two subsystems - a real-time robot audition subsystem and a dialog subsystem focusing on RPS sound games. The robot audition subsystem can recognize simultaneous speeches by exploiting two key ideas; preprocessing consisting of sound source localization and separation with a microphone array, and system integration based on missing feature theory (MFT). Preprocessing improves the SNR of a target sound signal using geometric source separation with a multi-channel post-filter. MFT uses only reliable acoustic features in speech recognition and masks out unreliable parts caused by interfering sounds and preprocessing. MFT thus provides smooth integration between preprocessing and automatic speech recognition. The dialog subsystem is implemented as a system-initiative dialog system for multiple players based on deterministic finite automata. It first waits for a trigger command to start an RPS sound game, controls the dialog with players in the game, and finally decides the winner of the game. The referee system is constructed for Honda ASIMO with an 8-ch microphone array. In the case with two players, we attained a 70% task completion rate for the games on average.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages3469-3474
Number of pages6
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE International Conference on Robotics and Automation, ICRA 2008 - Pasadena, CA
Duration: 2008 May 192008 May 23

Other

Other2008 IEEE International Conference on Robotics and Automation, ICRA 2008
CityPasadena, CA
Period08/5/1908/5/23

Fingerprint

Rocks
Acoustic waves
Robots
Audition
Microphones
Speech recognition
Signal to noise ratio
Source separation
Finite automata
Masks
Acoustics

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Cite this

Nakadai, K., Yamamoto, S., Okuno, H. G., Nakajima, H., Hasegawa, Y., & Tsujino, H. (2008). A robot referee for rock-paper-scissors sound games. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 3469-3474). [4543741] https://doi.org/10.1109/ROBOT.2008.4543741

A robot referee for rock-paper-scissors sound games. / Nakadai, Kazuhiro; Yamamoto, Shunichi; Okuno, Hiroshi G.; Nakajima, Hirofumi; Hasegawa, Yuji; Tsujino, Hiroshi.

Proceedings - IEEE International Conference on Robotics and Automation. 2008. p. 3469-3474 4543741.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakadai, K, Yamamoto, S, Okuno, HG, Nakajima, H, Hasegawa, Y & Tsujino, H 2008, A robot referee for rock-paper-scissors sound games. in Proceedings - IEEE International Conference on Robotics and Automation., 4543741, pp. 3469-3474, 2008 IEEE International Conference on Robotics and Automation, ICRA 2008, Pasadena, CA, 08/5/19. https://doi.org/10.1109/ROBOT.2008.4543741
Nakadai K, Yamamoto S, Okuno HG, Nakajima H, Hasegawa Y, Tsujino H. A robot referee for rock-paper-scissors sound games. In Proceedings - IEEE International Conference on Robotics and Automation. 2008. p. 3469-3474. 4543741 https://doi.org/10.1109/ROBOT.2008.4543741
Nakadai, Kazuhiro ; Yamamoto, Shunichi ; Okuno, Hiroshi G. ; Nakajima, Hirofumi ; Hasegawa, Yuji ; Tsujino, Hiroshi. / A robot referee for rock-paper-scissors sound games. Proceedings - IEEE International Conference on Robotics and Automation. 2008. pp. 3469-3474
@inproceedings{6be85348b4df458abfa48a91c9de382e,
title = "A robot referee for rock-paper-scissors sound games",
abstract = "This paper describes a robot referee for {"}rockpaper-scissors (RPS){"} sound games; the robot decides the winner from a combination of rock, paper and scissors uttered by two or three people simultaneously without using any visual information. In this referee task, the robot has to cope with speech with low signal-to-noise ratio (SNR) due to a mixture of speeches, robot motor noises, and ambient noises. Our robot referee system, thus, consists of two subsystems - a real-time robot audition subsystem and a dialog subsystem focusing on RPS sound games. The robot audition subsystem can recognize simultaneous speeches by exploiting two key ideas; preprocessing consisting of sound source localization and separation with a microphone array, and system integration based on missing feature theory (MFT). Preprocessing improves the SNR of a target sound signal using geometric source separation with a multi-channel post-filter. MFT uses only reliable acoustic features in speech recognition and masks out unreliable parts caused by interfering sounds and preprocessing. MFT thus provides smooth integration between preprocessing and automatic speech recognition. The dialog subsystem is implemented as a system-initiative dialog system for multiple players based on deterministic finite automata. It first waits for a trigger command to start an RPS sound game, controls the dialog with players in the game, and finally decides the winner of the game. The referee system is constructed for Honda ASIMO with an 8-ch microphone array. In the case with two players, we attained a 70{\%} task completion rate for the games on average.",
author = "Kazuhiro Nakadai and Shunichi Yamamoto and Okuno, {Hiroshi G.} and Hirofumi Nakajima and Yuji Hasegawa and Hiroshi Tsujino",
year = "2008",
doi = "10.1109/ROBOT.2008.4543741",
language = "English",
isbn = "9781424416479",
pages = "3469--3474",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - A robot referee for rock-paper-scissors sound games

AU - Nakadai, Kazuhiro

AU - Yamamoto, Shunichi

AU - Okuno, Hiroshi G.

AU - Nakajima, Hirofumi

AU - Hasegawa, Yuji

AU - Tsujino, Hiroshi

PY - 2008

Y1 - 2008

N2 - This paper describes a robot referee for "rockpaper-scissors (RPS)" sound games; the robot decides the winner from a combination of rock, paper and scissors uttered by two or three people simultaneously without using any visual information. In this referee task, the robot has to cope with speech with low signal-to-noise ratio (SNR) due to a mixture of speeches, robot motor noises, and ambient noises. Our robot referee system, thus, consists of two subsystems - a real-time robot audition subsystem and a dialog subsystem focusing on RPS sound games. The robot audition subsystem can recognize simultaneous speeches by exploiting two key ideas; preprocessing consisting of sound source localization and separation with a microphone array, and system integration based on missing feature theory (MFT). Preprocessing improves the SNR of a target sound signal using geometric source separation with a multi-channel post-filter. MFT uses only reliable acoustic features in speech recognition and masks out unreliable parts caused by interfering sounds and preprocessing. MFT thus provides smooth integration between preprocessing and automatic speech recognition. The dialog subsystem is implemented as a system-initiative dialog system for multiple players based on deterministic finite automata. It first waits for a trigger command to start an RPS sound game, controls the dialog with players in the game, and finally decides the winner of the game. The referee system is constructed for Honda ASIMO with an 8-ch microphone array. In the case with two players, we attained a 70% task completion rate for the games on average.

AB - This paper describes a robot referee for "rockpaper-scissors (RPS)" sound games; the robot decides the winner from a combination of rock, paper and scissors uttered by two or three people simultaneously without using any visual information. In this referee task, the robot has to cope with speech with low signal-to-noise ratio (SNR) due to a mixture of speeches, robot motor noises, and ambient noises. Our robot referee system, thus, consists of two subsystems - a real-time robot audition subsystem and a dialog subsystem focusing on RPS sound games. The robot audition subsystem can recognize simultaneous speeches by exploiting two key ideas; preprocessing consisting of sound source localization and separation with a microphone array, and system integration based on missing feature theory (MFT). Preprocessing improves the SNR of a target sound signal using geometric source separation with a multi-channel post-filter. MFT uses only reliable acoustic features in speech recognition and masks out unreliable parts caused by interfering sounds and preprocessing. MFT thus provides smooth integration between preprocessing and automatic speech recognition. The dialog subsystem is implemented as a system-initiative dialog system for multiple players based on deterministic finite automata. It first waits for a trigger command to start an RPS sound game, controls the dialog with players in the game, and finally decides the winner of the game. The referee system is constructed for Honda ASIMO with an 8-ch microphone array. In the case with two players, we attained a 70% task completion rate for the games on average.

UR - http://www.scopus.com/inward/record.url?scp=51649115852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51649115852&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2008.4543741

DO - 10.1109/ROBOT.2008.4543741

M3 - Conference contribution

SN - 9781424416479

SP - 3469

EP - 3474

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -