Automatic voice assignment tool for instant casting movie system

Yoshihiro Adachi, Shinichi Kawamoto, Tatsuo Yotsukura, Shigeo Morishima, Satoshi Nakamura

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

    2 Citations (Scopus)

    Abstract

    In Instant Casting movie System, a personal CG character is automatically generated. The character resembles a participant in a face geometry and texture. However, the voice of a character was an alternative voice determined by the gender of the participant. Therefore sometimes it's not enough to identify the personality of a CG character. In this paper, an automatic pre-scored voice assignment tool for a personal CG character is presented. Voice is essential to identify a personal character as well as a face feature. Our proposed system selects the most similar voice to the participants from voice database, and assigns it as a voice of CG character. Voice similarity criterion is presented by combination of eight acoustic features. After assigning voice data to a personal character, the voice track is played back in synchronization with the movement of the CG character. 60 voice variations have been prepared to our voice database. Validity of the assigned voice has been evaluated by MOS value. The proposed method has achieved 68% of the theoretical figure that is calculated by preliminary experiments.

    Original languageEnglish
    Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
    Pages1897-1900
    Number of pages4
    DOIs
    Publication statusPublished - 2009
    Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei
    Duration: 2009 Apr 192009 Apr 24

    Other

    Other2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
    CityTaipei
    Period09/4/1909/4/24

    Fingerprint

    Casting
    Synchronization
    Textures
    Acoustics
    Geometry

    Keywords

    • Computer applications
    • Speaker recognition
    • Speech analysis

    ASJC Scopus subject areas

    • Signal Processing
    • Software
    • Electrical and Electronic Engineering

    Cite this

    Adachi, Y., Kawamoto, S., Yotsukura, T., Morishima, S., & Nakamura, S. (2009). Automatic voice assignment tool for instant casting movie system. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 1897-1900). [4959979] https://doi.org/10.1109/ICASSP.2009.4959979

    Automatic voice assignment tool for instant casting movie system. / Adachi, Yoshihiro; Kawamoto, Shinichi; Yotsukura, Tatsuo; Morishima, Shigeo; Nakamura, Satoshi.

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 1897-1900 4959979.

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

    Adachi, Y, Kawamoto, S, Yotsukura, T, Morishima, S & Nakamura, S 2009, Automatic voice assignment tool for instant casting movie system. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4959979, pp. 1897-1900, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, 09/4/19. https://doi.org/10.1109/ICASSP.2009.4959979
    Adachi Y, Kawamoto S, Yotsukura T, Morishima S, Nakamura S. Automatic voice assignment tool for instant casting movie system. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 1897-1900. 4959979 https://doi.org/10.1109/ICASSP.2009.4959979
    Adachi, Yoshihiro ; Kawamoto, Shinichi ; Yotsukura, Tatsuo ; Morishima, Shigeo ; Nakamura, Satoshi. / Automatic voice assignment tool for instant casting movie system. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. pp. 1897-1900
    @inproceedings{2f967bfcd0aa471b8ce1fc0768509457,
    title = "Automatic voice assignment tool for instant casting movie system",
    abstract = "In Instant Casting movie System, a personal CG character is automatically generated. The character resembles a participant in a face geometry and texture. However, the voice of a character was an alternative voice determined by the gender of the participant. Therefore sometimes it's not enough to identify the personality of a CG character. In this paper, an automatic pre-scored voice assignment tool for a personal CG character is presented. Voice is essential to identify a personal character as well as a face feature. Our proposed system selects the most similar voice to the participants from voice database, and assigns it as a voice of CG character. Voice similarity criterion is presented by combination of eight acoustic features. After assigning voice data to a personal character, the voice track is played back in synchronization with the movement of the CG character. 60 voice variations have been prepared to our voice database. Validity of the assigned voice has been evaluated by MOS value. The proposed method has achieved 68{\%} of the theoretical figure that is calculated by preliminary experiments.",
    keywords = "Computer applications, Speaker recognition, Speech analysis",
    author = "Yoshihiro Adachi and Shinichi Kawamoto and Tatsuo Yotsukura and Shigeo Morishima and Satoshi Nakamura",
    year = "2009",
    doi = "10.1109/ICASSP.2009.4959979",
    language = "English",
    isbn = "9781424423545",
    pages = "1897--1900",
    booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

    }

    TY - GEN

    T1 - Automatic voice assignment tool for instant casting movie system

    AU - Adachi, Yoshihiro

    AU - Kawamoto, Shinichi

    AU - Yotsukura, Tatsuo

    AU - Morishima, Shigeo

    AU - Nakamura, Satoshi

    PY - 2009

    Y1 - 2009

    N2 - In Instant Casting movie System, a personal CG character is automatically generated. The character resembles a participant in a face geometry and texture. However, the voice of a character was an alternative voice determined by the gender of the participant. Therefore sometimes it's not enough to identify the personality of a CG character. In this paper, an automatic pre-scored voice assignment tool for a personal CG character is presented. Voice is essential to identify a personal character as well as a face feature. Our proposed system selects the most similar voice to the participants from voice database, and assigns it as a voice of CG character. Voice similarity criterion is presented by combination of eight acoustic features. After assigning voice data to a personal character, the voice track is played back in synchronization with the movement of the CG character. 60 voice variations have been prepared to our voice database. Validity of the assigned voice has been evaluated by MOS value. The proposed method has achieved 68% of the theoretical figure that is calculated by preliminary experiments.

    AB - In Instant Casting movie System, a personal CG character is automatically generated. The character resembles a participant in a face geometry and texture. However, the voice of a character was an alternative voice determined by the gender of the participant. Therefore sometimes it's not enough to identify the personality of a CG character. In this paper, an automatic pre-scored voice assignment tool for a personal CG character is presented. Voice is essential to identify a personal character as well as a face feature. Our proposed system selects the most similar voice to the participants from voice database, and assigns it as a voice of CG character. Voice similarity criterion is presented by combination of eight acoustic features. After assigning voice data to a personal character, the voice track is played back in synchronization with the movement of the CG character. 60 voice variations have been prepared to our voice database. Validity of the assigned voice has been evaluated by MOS value. The proposed method has achieved 68% of the theoretical figure that is calculated by preliminary experiments.

    KW - Computer applications

    KW - Speaker recognition

    KW - Speech analysis

    UR - http://www.scopus.com/inward/record.url?scp=70349220905&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70349220905&partnerID=8YFLogxK

    U2 - 10.1109/ICASSP.2009.4959979

    DO - 10.1109/ICASSP.2009.4959979

    M3 - Conference contribution

    AN - SCOPUS:70349220905

    SN - 9781424423545

    SP - 1897

    EP - 1900

    BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

    ER -