Automatic parameter optimization in epsilon-filter for acoustical signal processing utilizing correlation coefficient

Tomomi Abe, Shuji Hashimoto, Mitsuharu Matsumoto

    Research output: Contribution to journalArticle

    5 Citations (Scopus)

    Abstract

    ε -filter can reduce most kinds of noise from a single-channel noisy signal while preserving signals that vary drastically such as speech signals. It can reduce not only stationary noise but also nonstationary noise. However, it has some parameters whose values are set empirically. So far, there have been few studies to evaluate the appropriateness of the parameter settings for ε -filter. This paper employs the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter setting. This paper also describes the algorithm to set the optimal parameter value of ε -filter automatically. To evaluate the adequateness of the obtained parameter, the mean absolute error is calculated. The experimental results show that the adequate parameter in ε -filter can be obtained automatically by using the proposed method.

    Original languageEnglish
    Pages (from-to)896-901
    Number of pages6
    JournalJournal of the Acoustical Society of America
    Volume127
    Issue number2
    DOIs
    Publication statusPublished - 2010

    Fingerprint

    correlation coefficients
    signal processing
    filters
    optimization
    output
    preserving
    Signal Processing
    Correlation Coefficient
    Filter
    evaluation

    ASJC Scopus subject areas

    • Acoustics and Ultrasonics

    Cite this

    Automatic parameter optimization in epsilon-filter for acoustical signal processing utilizing correlation coefficient. / Abe, Tomomi; Hashimoto, Shuji; Matsumoto, Mitsuharu.

    In: Journal of the Acoustical Society of America, Vol. 127, No. 2, 2010, p. 896-901.

    Research output: Contribution to journalArticle

    @article{a3842868324248eb891fd602566515db,
    title = "Automatic parameter optimization in epsilon-filter for acoustical signal processing utilizing correlation coefficient",
    abstract = "ε -filter can reduce most kinds of noise from a single-channel noisy signal while preserving signals that vary drastically such as speech signals. It can reduce not only stationary noise but also nonstationary noise. However, it has some parameters whose values are set empirically. So far, there have been few studies to evaluate the appropriateness of the parameter settings for ε -filter. This paper employs the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter setting. This paper also describes the algorithm to set the optimal parameter value of ε -filter automatically. To evaluate the adequateness of the obtained parameter, the mean absolute error is calculated. The experimental results show that the adequate parameter in ε -filter can be obtained automatically by using the proposed method.",
    author = "Tomomi Abe and Shuji Hashimoto and Mitsuharu Matsumoto",
    year = "2010",
    doi = "10.1121/1.3278601",
    language = "English",
    volume = "127",
    pages = "896--901",
    journal = "Journal of the Acoustical Society of America",
    issn = "0001-4966",
    publisher = "Acoustical Society of America",
    number = "2",

    }

    TY - JOUR

    T1 - Automatic parameter optimization in epsilon-filter for acoustical signal processing utilizing correlation coefficient

    AU - Abe, Tomomi

    AU - Hashimoto, Shuji

    AU - Matsumoto, Mitsuharu

    PY - 2010

    Y1 - 2010

    N2 - ε -filter can reduce most kinds of noise from a single-channel noisy signal while preserving signals that vary drastically such as speech signals. It can reduce not only stationary noise but also nonstationary noise. However, it has some parameters whose values are set empirically. So far, there have been few studies to evaluate the appropriateness of the parameter settings for ε -filter. This paper employs the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter setting. This paper also describes the algorithm to set the optimal parameter value of ε -filter automatically. To evaluate the adequateness of the obtained parameter, the mean absolute error is calculated. The experimental results show that the adequate parameter in ε -filter can be obtained automatically by using the proposed method.

    AB - ε -filter can reduce most kinds of noise from a single-channel noisy signal while preserving signals that vary drastically such as speech signals. It can reduce not only stationary noise but also nonstationary noise. However, it has some parameters whose values are set empirically. So far, there have been few studies to evaluate the appropriateness of the parameter settings for ε -filter. This paper employs the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter setting. This paper also describes the algorithm to set the optimal parameter value of ε -filter automatically. To evaluate the adequateness of the obtained parameter, the mean absolute error is calculated. The experimental results show that the adequate parameter in ε -filter can be obtained automatically by using the proposed method.

    UR - http://www.scopus.com/inward/record.url?scp=76349097344&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=76349097344&partnerID=8YFLogxK

    U2 - 10.1121/1.3278601

    DO - 10.1121/1.3278601

    M3 - Article

    VL - 127

    SP - 896

    EP - 901

    JO - Journal of the Acoustical Society of America

    JF - Journal of the Acoustical Society of America

    SN - 0001-4966

    IS - 2

    ER -