Influence of lombard effect: Accuracy analysis of simulation-based assessments of noisy speech recognition systems for various recognition conditions

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    The accuracy of simulation-based assessments of speech recognition systems under noisy conditions is investigated with a focus on the influence of the Lombard effect on the speech recognition performances. This investigation was carried out under various recognition conditions of different sound pressure levels of ambient noise, for different recognition tasks, such as continuous speech recognition and spoken word recognition, and using different recognition systems, i.e., systems with and without adaptation of the acoustic models to ambient noise. Experimental results showed that accurate simulation was not always achieved when dry sources with neutral talking style were used, but it could be achieved if the dry sources that include the influence of the Lombard effect were used; the simulation in the latter case is accurate, irrespective of the recognition conditions.

    Original languageEnglish
    Pages (from-to)2244-2252
    Number of pages9
    JournalIEICE Transactions on Information and Systems
    VolumeE92-D
    Issue number11
    DOIs
    Publication statusPublished - 2009

    Fingerprint

    Speech recognition
    Acoustic noise
    Continuous speech recognition
    Acoustics
    Acoustic waves

    Keywords

    • Assessment
    • Lombard effect
    • Noisy speech recognition
    • Simulation

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Software
    • Artificial Intelligence
    • Hardware and Architecture
    • Computer Vision and Pattern Recognition

    Cite this

    @article{0b89a99d4910406e9f44bd4e021fb56b,
    title = "Influence of lombard effect: Accuracy analysis of simulation-based assessments of noisy speech recognition systems for various recognition conditions",
    abstract = "The accuracy of simulation-based assessments of speech recognition systems under noisy conditions is investigated with a focus on the influence of the Lombard effect on the speech recognition performances. This investigation was carried out under various recognition conditions of different sound pressure levels of ambient noise, for different recognition tasks, such as continuous speech recognition and spoken word recognition, and using different recognition systems, i.e., systems with and without adaptation of the acoustic models to ambient noise. Experimental results showed that accurate simulation was not always achieved when dry sources with neutral talking style were used, but it could be achieved if the dry sources that include the influence of the Lombard effect were used; the simulation in the latter case is accurate, irrespective of the recognition conditions.",
    keywords = "Assessment, Lombard effect, Noisy speech recognition, Simulation",
    author = "Tetsuji Ogawa and Tetsunori Kobayashi",
    year = "2009",
    doi = "10.1587/transinf.E92.D.2244",
    language = "English",
    volume = "E92-D",
    pages = "2244--2252",
    journal = "IEICE Transactions on Information and Systems",
    issn = "0916-8532",
    publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
    number = "11",

    }

    TY - JOUR

    T1 - Influence of lombard effect

    T2 - Accuracy analysis of simulation-based assessments of noisy speech recognition systems for various recognition conditions

    AU - Ogawa, Tetsuji

    AU - Kobayashi, Tetsunori

    PY - 2009

    Y1 - 2009

    N2 - The accuracy of simulation-based assessments of speech recognition systems under noisy conditions is investigated with a focus on the influence of the Lombard effect on the speech recognition performances. This investigation was carried out under various recognition conditions of different sound pressure levels of ambient noise, for different recognition tasks, such as continuous speech recognition and spoken word recognition, and using different recognition systems, i.e., systems with and without adaptation of the acoustic models to ambient noise. Experimental results showed that accurate simulation was not always achieved when dry sources with neutral talking style were used, but it could be achieved if the dry sources that include the influence of the Lombard effect were used; the simulation in the latter case is accurate, irrespective of the recognition conditions.

    AB - The accuracy of simulation-based assessments of speech recognition systems under noisy conditions is investigated with a focus on the influence of the Lombard effect on the speech recognition performances. This investigation was carried out under various recognition conditions of different sound pressure levels of ambient noise, for different recognition tasks, such as continuous speech recognition and spoken word recognition, and using different recognition systems, i.e., systems with and without adaptation of the acoustic models to ambient noise. Experimental results showed that accurate simulation was not always achieved when dry sources with neutral talking style were used, but it could be achieved if the dry sources that include the influence of the Lombard effect were used; the simulation in the latter case is accurate, irrespective of the recognition conditions.

    KW - Assessment

    KW - Lombard effect

    KW - Noisy speech recognition

    KW - Simulation

    UR - http://www.scopus.com/inward/record.url?scp=77950218600&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77950218600&partnerID=8YFLogxK

    U2 - 10.1587/transinf.E92.D.2244

    DO - 10.1587/transinf.E92.D.2244

    M3 - Article

    AN - SCOPUS:77950218600

    VL - E92-D

    SP - 2244

    EP - 2252

    JO - IEICE Transactions on Information and Systems

    JF - IEICE Transactions on Information and Systems

    SN - 0916-8532

    IS - 11

    ER -