Toward a quizmaster robot for speech-based multiparty interaction

Izaya Nishimuta, Katsutoshi Itoyama, Kazuyoshi Yoshii, Hiroshi G. Okuno

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    This paper presents an interactive quizmaster robot that can manage a multiparty speech-based quiz game. The basic flow of the quiz game is that (1) the robot reads a question, (2) one or more players answer it, and (3) the robot judges the correctness of the answers. We categorize such speech-based quiz games into school-type interaction and auction-type interaction. The former asks players to say 'Yes' to get the right to answer before answering a question and the latter allows players to directly answer a question without any advance notice. To realize such interaction, the robot needs the capability of recognizing utterances from multiple people using its own microphones (i.e. ears), even if those utterances are made simultaneously. To cope with such situations, the robot estimates which player made the fastest utterance and recognizes it by localizing and separating a mixture of audio signals. Experiments were conducted to evaluate the success rates of the fastest player identification and speech recognition. The results showed that the robot could identify the fastest speakers with a success rate of 90.0% more accurately than humans when only one speaker slightly preceded the other speakers. We found that although the success rate of speech recognition for the fastest speakers did not reach that of humans, the robot attains amusing quiz game interaction.

    Original languageEnglish
    Pages (from-to)1205-1219
    Number of pages15
    JournalAdvanced Robotics
    Volume29
    Issue number18
    DOIs
    Publication statusPublished - 2015 Sep 17

    Fingerprint

    Robots
    Speech recognition
    Microphones
    Experiments

    Keywords

    • auction-type interaction
    • fastest-voice-first-type quiz game
    • quizmaster robot
    • robot audition
    • school-type interaction

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Human-Computer Interaction
    • Computer Science Applications
    • Hardware and Architecture
    • Software

    Cite this

    Toward a quizmaster robot for speech-based multiparty interaction. / Nishimuta, Izaya; Itoyama, Katsutoshi; Yoshii, Kazuyoshi; Okuno, Hiroshi G.

    In: Advanced Robotics, Vol. 29, No. 18, 17.09.2015, p. 1205-1219.

    Research output: Contribution to journalArticle

    Nishimuta, Izaya ; Itoyama, Katsutoshi ; Yoshii, Kazuyoshi ; Okuno, Hiroshi G. / Toward a quizmaster robot for speech-based multiparty interaction. In: Advanced Robotics. 2015 ; Vol. 29, No. 18. pp. 1205-1219.
    @article{75df552cc7ba472fa9624f4aba8a445a,
    title = "Toward a quizmaster robot for speech-based multiparty interaction",
    abstract = "This paper presents an interactive quizmaster robot that can manage a multiparty speech-based quiz game. The basic flow of the quiz game is that (1) the robot reads a question, (2) one or more players answer it, and (3) the robot judges the correctness of the answers. We categorize such speech-based quiz games into school-type interaction and auction-type interaction. The former asks players to say 'Yes' to get the right to answer before answering a question and the latter allows players to directly answer a question without any advance notice. To realize such interaction, the robot needs the capability of recognizing utterances from multiple people using its own microphones (i.e. ears), even if those utterances are made simultaneously. To cope with such situations, the robot estimates which player made the fastest utterance and recognizes it by localizing and separating a mixture of audio signals. Experiments were conducted to evaluate the success rates of the fastest player identification and speech recognition. The results showed that the robot could identify the fastest speakers with a success rate of 90.0{\%} more accurately than humans when only one speaker slightly preceded the other speakers. We found that although the success rate of speech recognition for the fastest speakers did not reach that of humans, the robot attains amusing quiz game interaction.",
    keywords = "auction-type interaction, fastest-voice-first-type quiz game, quizmaster robot, robot audition, school-type interaction",
    author = "Izaya Nishimuta and Katsutoshi Itoyama and Kazuyoshi Yoshii and Okuno, {Hiroshi G.}",
    year = "2015",
    month = "9",
    day = "17",
    doi = "10.1080/01691864.2015.1079504",
    language = "English",
    volume = "29",
    pages = "1205--1219",
    journal = "Advanced Robotics",
    issn = "0169-1864",
    publisher = "Taylor and Francis Ltd.",
    number = "18",

    }

    TY - JOUR

    T1 - Toward a quizmaster robot for speech-based multiparty interaction

    AU - Nishimuta, Izaya

    AU - Itoyama, Katsutoshi

    AU - Yoshii, Kazuyoshi

    AU - Okuno, Hiroshi G.

    PY - 2015/9/17

    Y1 - 2015/9/17

    N2 - This paper presents an interactive quizmaster robot that can manage a multiparty speech-based quiz game. The basic flow of the quiz game is that (1) the robot reads a question, (2) one or more players answer it, and (3) the robot judges the correctness of the answers. We categorize such speech-based quiz games into school-type interaction and auction-type interaction. The former asks players to say 'Yes' to get the right to answer before answering a question and the latter allows players to directly answer a question without any advance notice. To realize such interaction, the robot needs the capability of recognizing utterances from multiple people using its own microphones (i.e. ears), even if those utterances are made simultaneously. To cope with such situations, the robot estimates which player made the fastest utterance and recognizes it by localizing and separating a mixture of audio signals. Experiments were conducted to evaluate the success rates of the fastest player identification and speech recognition. The results showed that the robot could identify the fastest speakers with a success rate of 90.0% more accurately than humans when only one speaker slightly preceded the other speakers. We found that although the success rate of speech recognition for the fastest speakers did not reach that of humans, the robot attains amusing quiz game interaction.

    AB - This paper presents an interactive quizmaster robot that can manage a multiparty speech-based quiz game. The basic flow of the quiz game is that (1) the robot reads a question, (2) one or more players answer it, and (3) the robot judges the correctness of the answers. We categorize such speech-based quiz games into school-type interaction and auction-type interaction. The former asks players to say 'Yes' to get the right to answer before answering a question and the latter allows players to directly answer a question without any advance notice. To realize such interaction, the robot needs the capability of recognizing utterances from multiple people using its own microphones (i.e. ears), even if those utterances are made simultaneously. To cope with such situations, the robot estimates which player made the fastest utterance and recognizes it by localizing and separating a mixture of audio signals. Experiments were conducted to evaluate the success rates of the fastest player identification and speech recognition. The results showed that the robot could identify the fastest speakers with a success rate of 90.0% more accurately than humans when only one speaker slightly preceded the other speakers. We found that although the success rate of speech recognition for the fastest speakers did not reach that of humans, the robot attains amusing quiz game interaction.

    KW - auction-type interaction

    KW - fastest-voice-first-type quiz game

    KW - quizmaster robot

    KW - robot audition

    KW - school-type interaction

    UR - http://www.scopus.com/inward/record.url?scp=84942866828&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84942866828&partnerID=8YFLogxK

    U2 - 10.1080/01691864.2015.1079504

    DO - 10.1080/01691864.2015.1079504

    M3 - Article

    AN - SCOPUS:84942866828

    VL - 29

    SP - 1205

    EP - 1219

    JO - Advanced Robotics

    JF - Advanced Robotics

    SN - 0169-1864

    IS - 18

    ER -