Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient

Tomomi Matsumoto, Mitsuharu Matsumoto, Shuji Hashimoto

    研究成果: Conference contribution

    抄録

    Time-Frequency ε-filter (TF ε-filter) can reduce different types of noise from a single-channel noisy signal while preserving the signal that varies drastically such as a speech signal. It can reduce not only small stationary noise but also large nonstationary noise. However, it has some parameters whose values are set empirically. So far, there are few studies to optimize the parameter of TF ε-filter automatically. In this paper, we employ the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter optimization. We also propose an algorithm to set the optimal parameter of TF ε-filter automatically. The experimental results show that we can obtain the adequate parameter in TF ε-filter automatically by using the proposed method.

    元の言語English
    ホスト出版物のタイトルSIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems
    ページ237-241
    ページ数5
    出版物ステータスPublished - 2012
    イベントInternational Conference on Signal Processing and Multimedia Applications, SIGMAP 2012 and International Conference on Wireless Information Networks and Systems, WINSYS 2012 - Rome
    継続期間: 2012 7 242012 7 27

    Other

    OtherInternational Conference on Signal Processing and Multimedia Applications, SIGMAP 2012 and International Conference on Wireless Information Networks and Systems, WINSYS 2012
    Rome
    期間12/7/2412/7/27

    Fingerprint

    Function evaluation
    Simulated annealing
    time
    evaluation
    Values

    ASJC Scopus subject areas

    • Information Systems
    • Signal Processing
    • Communication

    これを引用

    Matsumoto, T., Matsumoto, M., & Hashimoto, S. (2012). Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient. : SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems (pp. 237-241)

    Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient. / Matsumoto, Tomomi; Matsumoto, Mitsuharu; Hashimoto, Shuji.

    SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems. 2012. p. 237-241.

    研究成果: Conference contribution

    Matsumoto, T, Matsumoto, M & Hashimoto, S 2012, Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient. : SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems. pp. 237-241, International Conference on Signal Processing and Multimedia Applications, SIGMAP 2012 and International Conference on Wireless Information Networks and Systems, WINSYS 2012, Rome, 12/7/24.
    Matsumoto T, Matsumoto M, Hashimoto S. Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient. : SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems. 2012. p. 237-241
    Matsumoto, Tomomi ; Matsumoto, Mitsuharu ; Hashimoto, Shuji. / Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient. SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems. 2012. pp. 237-241
    @inproceedings{79ec96ba6b654e6a9df3df9f68e59b27,
    title = "Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient",
    abstract = "Time-Frequency ε-filter (TF ε-filter) can reduce different types of noise from a single-channel noisy signal while preserving the signal that varies drastically such as a speech signal. It can reduce not only small stationary noise but also large nonstationary noise. However, it has some parameters whose values are set empirically. So far, there are few studies to optimize the parameter of TF ε-filter automatically. In this paper, we employ the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter optimization. We also propose an algorithm to set the optimal parameter of TF ε-filter automatically. The experimental results show that we can obtain the adequate parameter in TF ε-filter automatically by using the proposed method.",
    keywords = "ε-filter, Noise reduction, Nonlinear filter, Parameter optimization, Simulated annealing, Time-Frequency ε-filter",
    author = "Tomomi Matsumoto and Mitsuharu Matsumoto and Shuji Hashimoto",
    year = "2012",
    language = "English",
    isbn = "9789898565259",
    pages = "237--241",
    booktitle = "SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems",

    }

    TY - GEN

    T1 - Simulated annealing based parameter optimization of Time-Frequency ε-filter utilizing correlation coefficient

    AU - Matsumoto, Tomomi

    AU - Matsumoto, Mitsuharu

    AU - Hashimoto, Shuji

    PY - 2012

    Y1 - 2012

    N2 - Time-Frequency ε-filter (TF ε-filter) can reduce different types of noise from a single-channel noisy signal while preserving the signal that varies drastically such as a speech signal. It can reduce not only small stationary noise but also large nonstationary noise. However, it has some parameters whose values are set empirically. So far, there are few studies to optimize the parameter of TF ε-filter automatically. In this paper, we employ the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter optimization. We also propose an algorithm to set the optimal parameter of TF ε-filter automatically. The experimental results show that we can obtain the adequate parameter in TF ε-filter automatically by using the proposed method.

    AB - Time-Frequency ε-filter (TF ε-filter) can reduce different types of noise from a single-channel noisy signal while preserving the signal that varies drastically such as a speech signal. It can reduce not only small stationary noise but also large nonstationary noise. However, it has some parameters whose values are set empirically. So far, there are few studies to optimize the parameter of TF ε-filter automatically. In this paper, we employ the correlation coefficient of the filter output and the difference between the filter input and output as the evaluation function of the parameter optimization. We also propose an algorithm to set the optimal parameter of TF ε-filter automatically. The experimental results show that we can obtain the adequate parameter in TF ε-filter automatically by using the proposed method.

    KW - ε-filter

    KW - Noise reduction

    KW - Nonlinear filter

    KW - Parameter optimization

    KW - Simulated annealing

    KW - Time-Frequency ε-filter

    UR - http://www.scopus.com/inward/record.url?scp=84867646546&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84867646546&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:84867646546

    SN - 9789898565259

    SP - 237

    EP - 241

    BT - SIGMAP 2012, WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems

    ER -