Fuzzy C-Means Clustering-Based Speaker Verification

Dat Tran, Max Wagner

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    16 Citations (Scopus)

    Abstract

    In speaker verification, a claimed speaker’s score is computed to accept or reject the speaker claim. Most of the current normalisation methods compute the score as the ratio of the claimed speaker’s and the impostors’ likelihood functions. Based on analysing false acceptance error occured by the current methods, we propose a fuzzy c-means clusteringbased normalisation method to find a better score which can reduce that error. Experiments performed on the TI46 and the ANDOSL speech corpora show better results for the proposed method
    Original languageEnglish
    Title of host publicationAFSS International Conference on Fuzzy Systems, AFSS 2002
    Subtitle of host publicationAdvances in Soft Computing
    EditorsN. R. Pal, M. Sugeno
    Place of PublicationGermany
    PublisherSpringer
    Pages318-324
    Number of pages7
    ISBN (Print)9783540431503
    DOIs
    Publication statusPublished - 2002
    Event2002 AFSS International Conference on Fuzzy Systems - Calcutta, India
    Duration: 3 Feb 20026 Feb 2002

    Conference

    Conference2002 AFSS International Conference on Fuzzy Systems
    CountryIndia
    CityCalcutta
    Period3/02/026/02/02

    Fingerprint

    Experiments

    Cite this

    Tran, D., & Wagner, M. (2002). Fuzzy C-Means Clustering-Based Speaker Verification. In N. R. Pal, & M. Sugeno (Eds.), AFSS International Conference on Fuzzy Systems, AFSS 2002: Advances in Soft Computing (pp. 318-324). Germany: Springer. https://doi.org/10.1007/3-540-45631-7_42
    Tran, Dat ; Wagner, Max. / Fuzzy C-Means Clustering-Based Speaker Verification. AFSS International Conference on Fuzzy Systems, AFSS 2002: Advances in Soft Computing. editor / N. R. Pal ; M. Sugeno. Germany : Springer, 2002. pp. 318-324
    @inproceedings{df107ee0510341b7b1da86405e2d1baf,
    title = "Fuzzy C-Means Clustering-Based Speaker Verification",
    abstract = "In speaker verification, a claimed speaker’s score is computed to accept or reject the speaker claim. Most of the current normalisation methods compute the score as the ratio of the claimed speaker’s and the impostors’ likelihood functions. Based on analysing false acceptance error occured by the current methods, we propose a fuzzy c-means clusteringbased normalisation method to find a better score which can reduce that error. Experiments performed on the TI46 and the ANDOSL speech corpora show better results for the proposed method",
    author = "Dat Tran and Max Wagner",
    year = "2002",
    doi = "10.1007/3-540-45631-7_42",
    language = "English",
    isbn = "9783540431503",
    pages = "318--324",
    editor = "Pal, {N. R.} and M. Sugeno",
    booktitle = "AFSS International Conference on Fuzzy Systems, AFSS 2002",
    publisher = "Springer",
    address = "Netherlands",

    }

    Tran, D & Wagner, M 2002, Fuzzy C-Means Clustering-Based Speaker Verification. in NR Pal & M Sugeno (eds), AFSS International Conference on Fuzzy Systems, AFSS 2002: Advances in Soft Computing. Springer, Germany, pp. 318-324, 2002 AFSS International Conference on Fuzzy Systems, Calcutta, India, 3/02/02. https://doi.org/10.1007/3-540-45631-7_42

    Fuzzy C-Means Clustering-Based Speaker Verification. / Tran, Dat; Wagner, Max.

    AFSS International Conference on Fuzzy Systems, AFSS 2002: Advances in Soft Computing. ed. / N. R. Pal; M. Sugeno. Germany : Springer, 2002. p. 318-324.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Fuzzy C-Means Clustering-Based Speaker Verification

    AU - Tran, Dat

    AU - Wagner, Max

    PY - 2002

    Y1 - 2002

    N2 - In speaker verification, a claimed speaker’s score is computed to accept or reject the speaker claim. Most of the current normalisation methods compute the score as the ratio of the claimed speaker’s and the impostors’ likelihood functions. Based on analysing false acceptance error occured by the current methods, we propose a fuzzy c-means clusteringbased normalisation method to find a better score which can reduce that error. Experiments performed on the TI46 and the ANDOSL speech corpora show better results for the proposed method

    AB - In speaker verification, a claimed speaker’s score is computed to accept or reject the speaker claim. Most of the current normalisation methods compute the score as the ratio of the claimed speaker’s and the impostors’ likelihood functions. Based on analysing false acceptance error occured by the current methods, we propose a fuzzy c-means clusteringbased normalisation method to find a better score which can reduce that error. Experiments performed on the TI46 and the ANDOSL speech corpora show better results for the proposed method

    U2 - 10.1007/3-540-45631-7_42

    DO - 10.1007/3-540-45631-7_42

    M3 - Conference contribution

    SN - 9783540431503

    SP - 318

    EP - 324

    BT - AFSS International Conference on Fuzzy Systems, AFSS 2002

    A2 - Pal, N. R.

    A2 - Sugeno, M.

    PB - Springer

    CY - Germany

    ER -

    Tran D, Wagner M. Fuzzy C-Means Clustering-Based Speaker Verification. In Pal NR, Sugeno M, editors, AFSS International Conference on Fuzzy Systems, AFSS 2002: Advances in Soft Computing. Germany: Springer. 2002. p. 318-324 https://doi.org/10.1007/3-540-45631-7_42