Communicative F0 generation based on impressions

Lu Shao, Yoko Greenberg, Yoshinori Sagisaka

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    1 Citation (Scopus)

    Abstract

    This paper introduces our research efforts of prosody control for so-called paralinguistic information embedded in communicative speech. To specify the output prosody, we employ three-dimensional expressions extracted from 26 impressions using Multi-Dimensional Scaling. Based on a series of our previous studies showing the correlations between impressions and prosody characteristics, we propose an exact computational scheme to obtain communicative F0 using impressions given by input lexicons and the F0 pattern of corresponding reading style speech. Experimental trials have confirmed the effectiveness of the proposed calculation scheme for a set of expressions consisting of lexicons forming impressions. Finally, further advanced problems are discussed to apply the proposed scheme to other expressions.

    Original languageEnglish
    Title of host publication5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages115-119
    Number of pages5
    ISBN (Electronic)9781479972807
    DOIs
    Publication statusPublished - 2014 Jan 23
    Event5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Vietri sul Mare
    Duration: 2014 Nov 5 → 2014 Nov 7

    Other

    Other5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014
    CityVietri sul Mare
    Period14/11/5 → 14/11/7

    Keywords

    • communicative speech synthesis
    • Fundamental frequency cotrol
    • impression
    • para-linguistics
    • speech prosody

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Networks and Communications
    • Information Systems
    • Signal Processing

    Cite this

    Shao, L., Greenberg, Y., & Sagisaka, Y. (2014). Communicative F0 generation based on impressions. In 5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings (pp. 115-119). [7020429] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CogInfoCom.2014.7020429

    Communicative F0 generation based on impressions. / Shao, Lu; Greenberg, Yoko; Sagisaka, Yoshinori.

    5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 115-119 7020429.

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    Shao, L, Greenberg, Y & Sagisaka, Y 2014, Communicative F0 generation based on impressions. in 5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings., 7020429, Institute of Electrical and Electronics Engineers Inc., pp. 115-119, 5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014, Vietri sul Mare, 14/11/5. https://doi.org/10.1109/CogInfoCom.2014.7020429
    Shao L, Greenberg Y, Sagisaka Y. Communicative F0 generation based on impressions. In 5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 115-119. 7020429 https://doi.org/10.1109/CogInfoCom.2014.7020429
    Shao, Lu ; Greenberg, Yoko ; Sagisaka, Yoshinori. / Communicative F0 generation based on impressions. 5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 115-119
    @inproceedings{0ff7f2b92bd04959a4d1487dd39df95a,
    title = "Communicative F0 generation based on impressions",
    abstract = "This paper introduces our research efforts of prosody control for so-called paralinguistic information embedded in communicative speech. To specify the output prosody, we employ three-dimensional expressions extracted from 26 impressions using Multi-Dimensional Scaling. Based on a series of our previous studies showing the correlations between impressions and prosody characteristics, we propose an exact computational scheme to obtain communicative F0 using impressions given by input lexicons and the F0 pattern of corresponding reading style speech. Experimental trials have confirmed the effectiveness of the proposed calculation scheme for a set of expressions consisting of lexicons forming impressions. Finally, further advanced problems are discussed to apply the proposed scheme to other expressions.",
    keywords = "communicative speech synthesis, Fundamental frequency cotrol, impression, para-linguistics, speech prosody",
    author = "Lu Shao and Yoko Greenberg and Yoshinori Sagisaka",
    year = "2014",
    month = "1",
    day = "23",
    doi = "10.1109/CogInfoCom.2014.7020429",
    language = "English",
    pages = "115--119",
    booktitle = "5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Communicative F0 generation based on impressions

    AU - Shao, Lu

    AU - Greenberg, Yoko

    AU - Sagisaka, Yoshinori

    PY - 2014/1/23

    Y1 - 2014/1/23

    N2 - This paper introduces our research efforts of prosody control for so-called paralinguistic information embedded in communicative speech. To specify the output prosody, we employ three-dimensional expressions extracted from 26 impressions using Multi-Dimensional Scaling. Based on a series of our previous studies showing the correlations between impressions and prosody characteristics, we propose an exact computational scheme to obtain communicative F0 using impressions given by input lexicons and the F0 pattern of corresponding reading style speech. Experimental trials have confirmed the effectiveness of the proposed calculation scheme for a set of expressions consisting of lexicons forming impressions. Finally, further advanced problems are discussed to apply the proposed scheme to other expressions.

    AB - This paper introduces our research efforts of prosody control for so-called paralinguistic information embedded in communicative speech. To specify the output prosody, we employ three-dimensional expressions extracted from 26 impressions using Multi-Dimensional Scaling. Based on a series of our previous studies showing the correlations between impressions and prosody characteristics, we propose an exact computational scheme to obtain communicative F0 using impressions given by input lexicons and the F0 pattern of corresponding reading style speech. Experimental trials have confirmed the effectiveness of the proposed calculation scheme for a set of expressions consisting of lexicons forming impressions. Finally, further advanced problems are discussed to apply the proposed scheme to other expressions.

    KW - communicative speech synthesis

    KW - Fundamental frequency cotrol

    KW - impression

    KW - para-linguistics

    KW - speech prosody

    UR - http://www.scopus.com/inward/record.url?scp=84988274600&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84988274600&partnerID=8YFLogxK

    U2 - 10.1109/CogInfoCom.2014.7020429

    DO - 10.1109/CogInfoCom.2014.7020429

    M3 - Conference contribution

    AN - SCOPUS:84988274600

    SP - 115

    EP - 119

    BT - 5th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2014 - Proceedings

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -

    Access to Document