Inter-language prosodic style modification experiment using word impression vector for communicative speech generation

Ke Li, Yoko Greenberg, Yoshinori Sagisaka

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

    4 Citations (Scopus)

    Abstract

    To confirm the language independency of a communicative prosody generation from input word impression vector, we synthesized communicative Mandarin speech using prosodic characteristics of communicative Japanese speech. The fundamental frequency and duration characteristics of one-word "n" utterances of Japanese were copied to Mandarin through input word attributes. From the subjective impressions of an input word, a three-dimensional vector was calculated through Multi-Dimensional Scaling analysis. Three dimensions reflecting impressions of confident-doubtful, allowable-unacceptable and positive-negative correspond to systematic prosodic variations; F0 height, F0 dynamics and duration. Subjective evaluation of synthesized speech showed the possibility of communicative prosody generation from input word impression vector language independently.

    Original languageEnglish
    Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    Pages1297-1300
    Number of pages4
    Volume2
    Publication statusPublished - 2007
    Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp
    Duration: 2007 Aug 272007 Aug 31

    Other

    Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
    CityAntwerp
    Period07/8/2707/8/31

    Fingerprint

    Prosody
    experiment
    language
    Experiment
    Subjective Evaluation
    Fundamental Frequency
    Experiments
    Three-dimension
    multidimensional scaling
    Attribute
    Scaling
    Three-dimensional
    Language
    Speech
    Style
    evaluation

    ASJC Scopus subject areas

    • Computer Science Applications
    • Software
    • Modelling and Simulation
    • Linguistics and Language
    • Communication

    Cite this

    Li, K., Greenberg, Y., & Sagisaka, Y. (2007). Inter-language prosodic style modification experiment using word impression vector for communicative speech generation. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2, pp. 1297-1300)

    Inter-language prosodic style modification experiment using word impression vector for communicative speech generation. / Li, Ke; Greenberg, Yoko; Sagisaka, Yoshinori.

    Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2 2007. p. 1297-1300.

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

    Li, K, Greenberg, Y & Sagisaka, Y 2007, Inter-language prosodic style modification experiment using word impression vector for communicative speech generation. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. 2, pp. 1297-1300, 8th Annual Conference of the International Speech Communication Association, Interspeech 2007, Antwerp, 07/8/27.
    Li K, Greenberg Y, Sagisaka Y. Inter-language prosodic style modification experiment using word impression vector for communicative speech generation. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2. 2007. p. 1297-1300
    Li, Ke ; Greenberg, Yoko ; Sagisaka, Yoshinori. / Inter-language prosodic style modification experiment using word impression vector for communicative speech generation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2 2007. pp. 1297-1300
    @inproceedings{8c809525c29d445f94b7e85f4d6bc9c4,
    title = "Inter-language prosodic style modification experiment using word impression vector for communicative speech generation",
    abstract = "To confirm the language independency of a communicative prosody generation from input word impression vector, we synthesized communicative Mandarin speech using prosodic characteristics of communicative Japanese speech. The fundamental frequency and duration characteristics of one-word {"}n{"} utterances of Japanese were copied to Mandarin through input word attributes. From the subjective impressions of an input word, a three-dimensional vector was calculated through Multi-Dimensional Scaling analysis. Three dimensions reflecting impressions of confident-doubtful, allowable-unacceptable and positive-negative correspond to systematic prosodic variations; F0 height, F0 dynamics and duration. Subjective evaluation of synthesized speech showed the possibility of communicative prosody generation from input word impression vector language independently.",
    author = "Ke Li and Yoko Greenberg and Yoshinori Sagisaka",
    year = "2007",
    language = "English",
    isbn = "9781605603162",
    volume = "2",
    pages = "1297--1300",
    booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

    }

    TY - GEN

    T1 - Inter-language prosodic style modification experiment using word impression vector for communicative speech generation

    AU - Li, Ke

    AU - Greenberg, Yoko

    AU - Sagisaka, Yoshinori

    PY - 2007

    Y1 - 2007

    N2 - To confirm the language independency of a communicative prosody generation from input word impression vector, we synthesized communicative Mandarin speech using prosodic characteristics of communicative Japanese speech. The fundamental frequency and duration characteristics of one-word "n" utterances of Japanese were copied to Mandarin through input word attributes. From the subjective impressions of an input word, a three-dimensional vector was calculated through Multi-Dimensional Scaling analysis. Three dimensions reflecting impressions of confident-doubtful, allowable-unacceptable and positive-negative correspond to systematic prosodic variations; F0 height, F0 dynamics and duration. Subjective evaluation of synthesized speech showed the possibility of communicative prosody generation from input word impression vector language independently.

    AB - To confirm the language independency of a communicative prosody generation from input word impression vector, we synthesized communicative Mandarin speech using prosodic characteristics of communicative Japanese speech. The fundamental frequency and duration characteristics of one-word "n" utterances of Japanese were copied to Mandarin through input word attributes. From the subjective impressions of an input word, a three-dimensional vector was calculated through Multi-Dimensional Scaling analysis. Three dimensions reflecting impressions of confident-doubtful, allowable-unacceptable and positive-negative correspond to systematic prosodic variations; F0 height, F0 dynamics and duration. Subjective evaluation of synthesized speech showed the possibility of communicative prosody generation from input word impression vector language independently.

    UR - http://www.scopus.com/inward/record.url?scp=56149126860&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=56149126860&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:56149126860

    SN - 9781605603162

    VL - 2

    SP - 1297

    EP - 1300

    BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

    ER -