Decomposition of monaural sound with unknown number of sources

Takuya Murayama, Shuji Hashimoto

    研究成果: Conference contribution

    抄録

    Humans possess an extremely flexible sound analysis ability to separate mixed sounds. Several methods, to realize automated sound source separation, have been proposed. The most of them assume certain assumptions on the measurement and the sound sources such as multiple microphones and non-overlapping spectra. It is better to make the assumptions looser. We have also proposed a monaural-sound source separation algorithm based on the time change differences of the power spectra for mostly overlapping sounds. However, the algorithm assumes that the mixed sound is composed of two sounds. In this paper, we propose an improved monaural-sound source separation algorithm, which can separate a mixed sound composed of more than two sounds without the knowledge of the sound source number.

    本文言語English
    ホスト出版物のタイトルProceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006
    ページ436-442
    ページ数7
    出版ステータスPublished - 2006
    イベント8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006 - Honolulu, HI
    継続期間: 2006 8 142006 8 16

    Other

    Other8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006
    CityHonolulu, HI
    Period06/8/1406/8/16

    ASJC Scopus subject areas

    • コンピュータ ビジョンおよびパターン認識
    • 信号処理

    フィンガープリント

    「Decomposition of monaural sound with unknown number of sources」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル