Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot

Naoya Mochiki, Toshiyuki Sekiya, Tetsuji Ogawa, Tetsunori Kobayashi

    研究成果: Conference contribution

    3 引用 (Scopus)

    抄録

    A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.

    元の言語English
    ホスト出版物のタイトル8th International Conference on Spoken Language Processing, ICSLP 2004
    出版者International Speech Communication Association
    ページ821-824
    ページ数4
    出版物ステータスPublished - 2004
    イベント8th International Conference on Spoken Language Processing, ICSLP 2004 - Jeju, Jeju Island, Korea, Republic of
    継続期間: 2004 10 42004 10 8

    Other

    Other8th International Conference on Spoken Language Processing, ICSLP 2004
    Korea, Republic of
    Jeju, Jeju Island
    期間04/10/404/10/8

    Fingerprint

    robot
    vocabulary
    Sound
    Robot
    Utterance

    ASJC Scopus subject areas

    • Language and Linguistics
    • Linguistics and Language

    これを引用

    Mochiki, N., Sekiya, T., Ogawa, T., & Kobayashi, T. (2004). Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. : 8th International Conference on Spoken Language Processing, ICSLP 2004 (pp. 821-824). International Speech Communication Association.

    Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. / Mochiki, Naoya; Sekiya, Toshiyuki; Ogawa, Tetsuji; Kobayashi, Tetsunori.

    8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, 2004. p. 821-824.

    研究成果: Conference contribution

    Mochiki, N, Sekiya, T, Ogawa, T & Kobayashi, T 2004, Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. : 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, pp. 821-824, 8th International Conference on Spoken Language Processing, ICSLP 2004, Jeju, Jeju Island, Korea, Republic of, 04/10/4.
    Mochiki N, Sekiya T, Ogawa T, Kobayashi T. Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. : 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association. 2004. p. 821-824
    Mochiki, Naoya ; Sekiya, Toshiyuki ; Ogawa, Tetsuji ; Kobayashi, Tetsunori. / Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot. 8th International Conference on Spoken Language Processing, ICSLP 2004. International Speech Communication Association, 2004. pp. 821-824
    @inproceedings{bb942d155a3243c29b3aa2b187c14401,
    title = "Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot",
    abstract = "A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71{\%} error reduction.",
    author = "Naoya Mochiki and Toshiyuki Sekiya and Tetsuji Ogawa and Tetsunori Kobayashi",
    year = "2004",
    language = "English",
    pages = "821--824",
    booktitle = "8th International Conference on Spoken Language Processing, ICSLP 2004",
    publisher = "International Speech Communication Association",

    }

    TY - GEN

    T1 - Recognition of three simultaneous utterance of speech by four-line directivity microphone mounted on head of robot

    AU - Mochiki, Naoya

    AU - Sekiya, Toshiyuki

    AU - Ogawa, Tetsuji

    AU - Kobayashi, Tetsunori

    PY - 2004

    Y1 - 2004

    N2 - A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.

    AB - A sound source separation method using four-line directivity microphones mounted on a head of a robot is proposed and applied to speech recognition under existence of two disturbances of speech. Sound source separation methods using microphones mounted on robot heads generally used strict head-related transfer functions(HRTF). We propose a robust sound source separation that does not require an estimate of a strict HRTF. Our method takes advantage of a sound pressure difference with the robot head acting as a sound barrier. The enhancement of the difference in the target speech is performed by signal processing of three layers:two-line SAFIA, two-line Spectral Subtraction and their integration. The experimental results of three simultaneous utterance recognition with vocabulary of 20K show that the proposed method is effective in achieving 71% error reduction.

    UR - http://www.scopus.com/inward/record.url?scp=85009121653&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85009121653&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:85009121653

    SP - 821

    EP - 824

    BT - 8th International Conference on Spoken Language Processing, ICSLP 2004

    PB - International Speech Communication Association

    ER -