Estimation of speaking style in speech corpora focusing on speech transcriptions

Raymond Shen, Hideaki Kikuchi

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

    Abstract

    Recent developments in computer technology have allowed the construction and widespread application of large-scale speech corpora. To foster ease of data retrieval for people interested in utilising these speech corpora, we attempt to characterise speaking style across some of them. In this paper, we first introduce the 3 scales of speaking style proposed by Eskenazi in 1993. We then use morphological features extracted from speech transcriptions that have proven effective in style discrimination and author identification in the field of natural language processing to construct an estimation model of speaking style. More specifically, we randomly choose transcriptions from various speech corpora as text stimuli with which to conduct a rating experiment on speaking style perception; then, using the features extracted from those stimuli and the rating results, we construct an estimation model of speaking style by a multi-regression analysis. After the cross validation (leave-1-out), the results show that among the 3 scales of speaking style, the ratings of 2 scales can be estimated with high accuracies, which prove the effectiveness of our method in the estimation of speaking style.

    Original languageEnglish
    Title of host publicationProceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014
    PublisherEuropean Language Resources Association (ELRA)
    Pages2747-2752
    Number of pages6
    ISBN (Electronic)9782951740884
    Publication statusPublished - 2014 Jan 1
    Event9th International Conference on Language Resources and Evaluation, LREC 2014 - Reykjavik, Iceland
    Duration: 2014 May 262014 May 31

    Other

    Other9th International Conference on Language Resources and Evaluation, LREC 2014
    CountryIceland
    CityReykjavik
    Period14/5/2614/5/31

    Fingerprint

    speaking
    rating
    stimulus
    Transcription
    regression analysis
    discrimination
    experiment
    language
    Rating

    Keywords

    • Estimation
    • Speaking style
    • Transcriptions

    ASJC Scopus subject areas

    • Linguistics and Language
    • Library and Information Sciences
    • Education
    • Language and Linguistics

    Cite this

    Shen, R., & Kikuchi, H. (2014). Estimation of speaking style in speech corpora focusing on speech transcriptions. In Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014 (pp. 2747-2752). European Language Resources Association (ELRA).

    Estimation of speaking style in speech corpora focusing on speech transcriptions. / Shen, Raymond; Kikuchi, Hideaki.

    Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), 2014. p. 2747-2752.

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

    Shen, R & Kikuchi, H 2014, Estimation of speaking style in speech corpora focusing on speech transcriptions. in Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), pp. 2747-2752, 9th International Conference on Language Resources and Evaluation, LREC 2014, Reykjavik, Iceland, 14/5/26.
    Shen R, Kikuchi H. Estimation of speaking style in speech corpora focusing on speech transcriptions. In Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA). 2014. p. 2747-2752
    Shen, Raymond ; Kikuchi, Hideaki. / Estimation of speaking style in speech corpora focusing on speech transcriptions. Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), 2014. pp. 2747-2752
    @inproceedings{1dc7ac33d9e9465aac4069b342466d94,
    title = "Estimation of speaking style in speech corpora focusing on speech transcriptions",
    abstract = "Recent developments in computer technology have allowed the construction and widespread application of large-scale speech corpora. To foster ease of data retrieval for people interested in utilising these speech corpora, we attempt to characterise speaking style across some of them. In this paper, we first introduce the 3 scales of speaking style proposed by Eskenazi in 1993. We then use morphological features extracted from speech transcriptions that have proven effective in style discrimination and author identification in the field of natural language processing to construct an estimation model of speaking style. More specifically, we randomly choose transcriptions from various speech corpora as text stimuli with which to conduct a rating experiment on speaking style perception; then, using the features extracted from those stimuli and the rating results, we construct an estimation model of speaking style by a multi-regression analysis. After the cross validation (leave-1-out), the results show that among the 3 scales of speaking style, the ratings of 2 scales can be estimated with high accuracies, which prove the effectiveness of our method in the estimation of speaking style.",
    keywords = "Estimation, Speaking style, Transcriptions",
    author = "Raymond Shen and Hideaki Kikuchi",
    year = "2014",
    month = "1",
    day = "1",
    language = "English",
    pages = "2747--2752",
    booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
    publisher = "European Language Resources Association (ELRA)",

    }

    TY - GEN

    T1 - Estimation of speaking style in speech corpora focusing on speech transcriptions

    AU - Shen, Raymond

    AU - Kikuchi, Hideaki

    PY - 2014/1/1

    Y1 - 2014/1/1

    N2 - Recent developments in computer technology have allowed the construction and widespread application of large-scale speech corpora. To foster ease of data retrieval for people interested in utilising these speech corpora, we attempt to characterise speaking style across some of them. In this paper, we first introduce the 3 scales of speaking style proposed by Eskenazi in 1993. We then use morphological features extracted from speech transcriptions that have proven effective in style discrimination and author identification in the field of natural language processing to construct an estimation model of speaking style. More specifically, we randomly choose transcriptions from various speech corpora as text stimuli with which to conduct a rating experiment on speaking style perception; then, using the features extracted from those stimuli and the rating results, we construct an estimation model of speaking style by a multi-regression analysis. After the cross validation (leave-1-out), the results show that among the 3 scales of speaking style, the ratings of 2 scales can be estimated with high accuracies, which prove the effectiveness of our method in the estimation of speaking style.

    AB - Recent developments in computer technology have allowed the construction and widespread application of large-scale speech corpora. To foster ease of data retrieval for people interested in utilising these speech corpora, we attempt to characterise speaking style across some of them. In this paper, we first introduce the 3 scales of speaking style proposed by Eskenazi in 1993. We then use morphological features extracted from speech transcriptions that have proven effective in style discrimination and author identification in the field of natural language processing to construct an estimation model of speaking style. More specifically, we randomly choose transcriptions from various speech corpora as text stimuli with which to conduct a rating experiment on speaking style perception; then, using the features extracted from those stimuli and the rating results, we construct an estimation model of speaking style by a multi-regression analysis. After the cross validation (leave-1-out), the results show that among the 3 scales of speaking style, the ratings of 2 scales can be estimated with high accuracies, which prove the effectiveness of our method in the estimation of speaking style.

    KW - Estimation

    KW - Speaking style

    KW - Transcriptions

    UR - http://www.scopus.com/inward/record.url?scp=85037124545&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85037124545&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:85037124545

    SP - 2747

    EP - 2752

    BT - Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014

    PB - European Language Resources Association (ELRA)

    ER -