A method for solving the permutation problem of frequency-domain BSS using reference signal

Takashi Isa, Toshiyuki Sekiya, Tetsuji Ogawa, Tetsunori Kobayashi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    This paper presents a method for solving the permutation problem. This is a problem specific to frequency domain blind source separation within the framework of independent component analysis. Towards this problem, we propose a method which uses reference signals. For each frequency bin, the permutation alignment is fixed by calculating correlation coefficients between the reference signal and the separated signal. Reference signals are obtained as signals corresponding to each individual original sources. The reference signals are chosen or obtained subjectively, and do not need to be separated well. For example, the conventional beamforming technique gives suitable reference signals. To show the effectiveness of this method, we conducted a experiment of continuous speech recognition in a real room. The experimental results of double talk recognition with 20K vocabulary show that the proposed method is effective to achieve 20% error reduction rate compared with the established DOA-based approach.

    Original languageEnglish
    Title of host publicationEuropean Signal Processing Conference
    Publication statusPublished - 2006
    Event14th European Signal Processing Conference, EUSIPCO 2006 - Florence, Italy
    Duration: 2006 Sep 42006 Sep 8

    Other

    Other14th European Signal Processing Conference, EUSIPCO 2006
    CountryItaly
    CityFlorence
    Period06/9/406/9/8

    Fingerprint

    Continuous speech recognition
    Blind source separation
    Independent component analysis
    Bins
    Beamforming
    Experiments

    ASJC Scopus subject areas

    • Signal Processing
    • Electrical and Electronic Engineering

    Cite this

    A method for solving the permutation problem of frequency-domain BSS using reference signal. / Isa, Takashi; Sekiya, Toshiyuki; Ogawa, Tetsuji; Kobayashi, Tetsunori.

    European Signal Processing Conference. 2006.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Isa, T, Sekiya, T, Ogawa, T & Kobayashi, T 2006, A method for solving the permutation problem of frequency-domain BSS using reference signal. in European Signal Processing Conference. 14th European Signal Processing Conference, EUSIPCO 2006, Florence, Italy, 06/9/4.
    @inproceedings{e2639add713340139cc33ea6b4e20b1d,
    title = "A method for solving the permutation problem of frequency-domain BSS using reference signal",
    abstract = "This paper presents a method for solving the permutation problem. This is a problem specific to frequency domain blind source separation within the framework of independent component analysis. Towards this problem, we propose a method which uses reference signals. For each frequency bin, the permutation alignment is fixed by calculating correlation coefficients between the reference signal and the separated signal. Reference signals are obtained as signals corresponding to each individual original sources. The reference signals are chosen or obtained subjectively, and do not need to be separated well. For example, the conventional beamforming technique gives suitable reference signals. To show the effectiveness of this method, we conducted a experiment of continuous speech recognition in a real room. The experimental results of double talk recognition with 20K vocabulary show that the proposed method is effective to achieve 20{\%} error reduction rate compared with the established DOA-based approach.",
    author = "Takashi Isa and Toshiyuki Sekiya and Tetsuji Ogawa and Tetsunori Kobayashi",
    year = "2006",
    language = "English",
    booktitle = "European Signal Processing Conference",

    }

    TY - GEN

    T1 - A method for solving the permutation problem of frequency-domain BSS using reference signal

    AU - Isa, Takashi

    AU - Sekiya, Toshiyuki

    AU - Ogawa, Tetsuji

    AU - Kobayashi, Tetsunori

    PY - 2006

    Y1 - 2006

    N2 - This paper presents a method for solving the permutation problem. This is a problem specific to frequency domain blind source separation within the framework of independent component analysis. Towards this problem, we propose a method which uses reference signals. For each frequency bin, the permutation alignment is fixed by calculating correlation coefficients between the reference signal and the separated signal. Reference signals are obtained as signals corresponding to each individual original sources. The reference signals are chosen or obtained subjectively, and do not need to be separated well. For example, the conventional beamforming technique gives suitable reference signals. To show the effectiveness of this method, we conducted a experiment of continuous speech recognition in a real room. The experimental results of double talk recognition with 20K vocabulary show that the proposed method is effective to achieve 20% error reduction rate compared with the established DOA-based approach.

    AB - This paper presents a method for solving the permutation problem. This is a problem specific to frequency domain blind source separation within the framework of independent component analysis. Towards this problem, we propose a method which uses reference signals. For each frequency bin, the permutation alignment is fixed by calculating correlation coefficients between the reference signal and the separated signal. Reference signals are obtained as signals corresponding to each individual original sources. The reference signals are chosen or obtained subjectively, and do not need to be separated well. For example, the conventional beamforming technique gives suitable reference signals. To show the effectiveness of this method, we conducted a experiment of continuous speech recognition in a real room. The experimental results of double talk recognition with 20K vocabulary show that the proposed method is effective to achieve 20% error reduction rate compared with the established DOA-based approach.

    UR - http://www.scopus.com/inward/record.url?scp=84862630399&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84862630399&partnerID=8YFLogxK

    M3 - Conference contribution

    BT - European Signal Processing Conference

    ER -