Discriminative non-negative matrix factorization with majorization-minimization

Li Li, Hirokazu Kameoka, Shoji Makino

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

Non-negative matrix factorization (NMF) is a powerful approach to single channel audio source separation. In a supervised setting, NMF is first applied to train the basis spectra of each sound source. At test time, NMF is applied to the spectrogram of a mixture signal using the pretrained spectra. The source signals can then be separated out using a Wiener filter. A typical way to train the basis spectra of each source is to minimize the objective function of NMF. However, the basis spectra obtained in this way do not ensure that the separated signal will be optimal at test time due to the inconsistency between the objective functions for training and separation (Wiener filtering). To address this, a framework called discriminative NMF (DNMF) has recently been proposed. In in this work a multiplicative update algorithm was proposed for the basis training, however one drawback is that the convergence is not guaranteed. To overcome this drawback, this paper proposes using a majorization-minimization principle to develop a convergence-guaranteed algorithm for DNMF. Experimental results showed that the proposed algorithm outperformed standard NMF and DNMF using a multiplicative update algorithm as regards both the signal-to-distortion and signal-to-interference ratios.

本文言語English
ホスト出版物のタイトル2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ141-145
ページ数5
ISBN(電子版)9781509059256
DOI
出版ステータスPublished - 2017 4 10
外部発表はい
イベント2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - San Francisco, United States
継続期間: 2017 3 12017 3 3

出版物シリーズ

名前2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings

Conference

Conference2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017
国/地域United States
CitySan Francisco
Period17/3/117/3/3

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ネットワークおよび通信
  • 音響学および超音波学
  • 器械工学
  • 通信

フィンガープリント

「Discriminative non-negative matrix factorization with majorization-minimization」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