Multichannel sound source dereverberation and separation for arbitrary number of sources based on Bayesian nonparametrics

Takuma Otsuka, Katsuhiko Ishiguro, Takuya Yoshioka, Hiroshi Sawada, Hiroshi G. Okuno

    Research output: Contribution to journalArticle

    9 Citations (Scopus)

    Abstract

    Multichannel signal processing using a microphone array provides fundamental functions for copingwith multi-source situations, such as sound source localization and separation, that are needed to extract the auditory information for each source. Auditory uncertainties about the degree of reverberation and the number of sources are known to degrade performance or limit the practical application of microphone array processing. Such uncertainties must therefore be overcome to realize general and robust microphone array processing. These uncertainty issues have been partly addressed-existing methods focus on either source number uncertainty or the reverberation issue, where joint separation and dereverberation has been achieved only for the overdetermined conditions. This paper presents an all-round method that achieves source separation and dereverberation for an arbitrary number of sources including underdetermined conditions. Our method uses Bayesian nonparametrics that realize an infinitely extensible modeling flexibility so as to bypass the model selection in the separation and dereverberation problem, which is caused by the source number uncertainty. Evaluation using a dereverberation and separation task with various numbers of sources including underdetermined conditions demonstrates that (1) ourmethod is applicable to the separation and dereverberation of underdetermined mixtures, and that (2) the source extraction performance is comparable to that of a state-of-the-art method suitable only for overdetermined conditions.

    Original languageEnglish
    Article number6926796
    Pages (from-to)2218-2232
    Number of pages15
    JournalIEEE/ACM Transactions on Speech and Language Processing
    Volume22
    Issue number12
    DOIs
    Publication statusPublished - 2014 Dec 1

    Fingerprint

    Bayesian Nonparametrics
    Uncertainty
    Acoustic waves
    uncertainty
    Microphones
    acoustics
    Arbitrary
    Array processing
    Microphone Array
    Reverberation
    Source Separation
    microphones
    Sound Localization
    Source separation
    Bayes Theorem
    reverberation
    performance
    Signal processing
    Source Localization
    flexibility

    Keywords

    • Bayesian nonparametrics
    • Blind dereverberation
    • Blind source separation
    • Markov chain Monte Carlo method
    • Microphone array processing
    • Underdetermined mixtures

    ASJC Scopus subject areas

    • Signal Processing
    • Electrical and Electronic Engineering
    • Media Technology
    • Acoustics and Ultrasonics
    • Instrumentation
    • Linguistics and Language
    • Speech and Hearing

    Cite this

    Multichannel sound source dereverberation and separation for arbitrary number of sources based on Bayesian nonparametrics. / Otsuka, Takuma; Ishiguro, Katsuhiko; Yoshioka, Takuya; Sawada, Hiroshi; Okuno, Hiroshi G.

    In: IEEE/ACM Transactions on Speech and Language Processing, Vol. 22, No. 12, 6926796, 01.12.2014, p. 2218-2232.

    Research output: Contribution to journalArticle

    @article{60e8f8a6590745b8a71ca75b2709ad92,
    title = "Multichannel sound source dereverberation and separation for arbitrary number of sources based on Bayesian nonparametrics",
    abstract = "Multichannel signal processing using a microphone array provides fundamental functions for copingwith multi-source situations, such as sound source localization and separation, that are needed to extract the auditory information for each source. Auditory uncertainties about the degree of reverberation and the number of sources are known to degrade performance or limit the practical application of microphone array processing. Such uncertainties must therefore be overcome to realize general and robust microphone array processing. These uncertainty issues have been partly addressed-existing methods focus on either source number uncertainty or the reverberation issue, where joint separation and dereverberation has been achieved only for the overdetermined conditions. This paper presents an all-round method that achieves source separation and dereverberation for an arbitrary number of sources including underdetermined conditions. Our method uses Bayesian nonparametrics that realize an infinitely extensible modeling flexibility so as to bypass the model selection in the separation and dereverberation problem, which is caused by the source number uncertainty. Evaluation using a dereverberation and separation task with various numbers of sources including underdetermined conditions demonstrates that (1) ourmethod is applicable to the separation and dereverberation of underdetermined mixtures, and that (2) the source extraction performance is comparable to that of a state-of-the-art method suitable only for overdetermined conditions.",
    keywords = "Bayesian nonparametrics, Blind dereverberation, Blind source separation, Markov chain Monte Carlo method, Microphone array processing, Underdetermined mixtures",
    author = "Takuma Otsuka and Katsuhiko Ishiguro and Takuya Yoshioka and Hiroshi Sawada and Okuno, {Hiroshi G.}",
    year = "2014",
    month = "12",
    day = "1",
    doi = "10.1109/TASLP.2014.2363790",
    language = "English",
    volume = "22",
    pages = "2218--2232",
    journal = "IEEE/ACM Transactions on Speech and Language Processing",
    issn = "2329-9290",
    publisher = "IEEE Advancing Technology for Humanity",
    number = "12",

    }

    TY - JOUR

    T1 - Multichannel sound source dereverberation and separation for arbitrary number of sources based on Bayesian nonparametrics

    AU - Otsuka, Takuma

    AU - Ishiguro, Katsuhiko

    AU - Yoshioka, Takuya

    AU - Sawada, Hiroshi

    AU - Okuno, Hiroshi G.

    PY - 2014/12/1

    Y1 - 2014/12/1

    N2 - Multichannel signal processing using a microphone array provides fundamental functions for copingwith multi-source situations, such as sound source localization and separation, that are needed to extract the auditory information for each source. Auditory uncertainties about the degree of reverberation and the number of sources are known to degrade performance or limit the practical application of microphone array processing. Such uncertainties must therefore be overcome to realize general and robust microphone array processing. These uncertainty issues have been partly addressed-existing methods focus on either source number uncertainty or the reverberation issue, where joint separation and dereverberation has been achieved only for the overdetermined conditions. This paper presents an all-round method that achieves source separation and dereverberation for an arbitrary number of sources including underdetermined conditions. Our method uses Bayesian nonparametrics that realize an infinitely extensible modeling flexibility so as to bypass the model selection in the separation and dereverberation problem, which is caused by the source number uncertainty. Evaluation using a dereverberation and separation task with various numbers of sources including underdetermined conditions demonstrates that (1) ourmethod is applicable to the separation and dereverberation of underdetermined mixtures, and that (2) the source extraction performance is comparable to that of a state-of-the-art method suitable only for overdetermined conditions.

    AB - Multichannel signal processing using a microphone array provides fundamental functions for copingwith multi-source situations, such as sound source localization and separation, that are needed to extract the auditory information for each source. Auditory uncertainties about the degree of reverberation and the number of sources are known to degrade performance or limit the practical application of microphone array processing. Such uncertainties must therefore be overcome to realize general and robust microphone array processing. These uncertainty issues have been partly addressed-existing methods focus on either source number uncertainty or the reverberation issue, where joint separation and dereverberation has been achieved only for the overdetermined conditions. This paper presents an all-round method that achieves source separation and dereverberation for an arbitrary number of sources including underdetermined conditions. Our method uses Bayesian nonparametrics that realize an infinitely extensible modeling flexibility so as to bypass the model selection in the separation and dereverberation problem, which is caused by the source number uncertainty. Evaluation using a dereverberation and separation task with various numbers of sources including underdetermined conditions demonstrates that (1) ourmethod is applicable to the separation and dereverberation of underdetermined mixtures, and that (2) the source extraction performance is comparable to that of a state-of-the-art method suitable only for overdetermined conditions.

    KW - Bayesian nonparametrics

    KW - Blind dereverberation

    KW - Blind source separation

    KW - Markov chain Monte Carlo method

    KW - Microphone array processing

    KW - Underdetermined mixtures

    UR - http://www.scopus.com/inward/record.url?scp=84921811850&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84921811850&partnerID=8YFLogxK

    U2 - 10.1109/TASLP.2014.2363790

    DO - 10.1109/TASLP.2014.2363790

    M3 - Article

    AN - SCOPUS:84921811850

    VL - 22

    SP - 2218

    EP - 2232

    JO - IEEE/ACM Transactions on Speech and Language Processing

    JF - IEEE/ACM Transactions on Speech and Language Processing

    SN - 2329-9290

    IS - 12

    M1 - 6926796

    ER -