Mel-Generalized cepstral regularization for discriminative non-negative matrix factorization

Li Li, Hirokazu Kameoka, Shoji Makino

研究成果: Conference contribution

抄録

The non-negative matrix factorization (NMF) approach has shown to work reasonably well for monaural speech enhancement tasks. This paper proposes addressing two shortcomings of the original NMF approach: (1) the objective functions for the basis training and separation (Wiener filtering) are inconsistent (the basis spectra are not trained so that the separated signal becomes optimal); (2) minimizing spectral divergence measures does not necessarily lead to an enhancement in the feature domain (e.g., cepstral domain) or in terms of perceived quality. To address the first shortcoming, we have previously proposed an algorithm for Discriminative NMF (DNMF), which optimizes the same objective for basis training and separation. To address the second shortcoming, we have previously introduced novel frameworks called the cepstral distance regularized NMF (CDRNMF) and mel-generalized cepstral distance regularized NMF (MGCRNMF), which aim to enhance speech both in the spectral domain and feature domain. This paper proposes combining the goals of DNMF and MGCRNMF by incorporating the MGC regularizer into the DNMF objective function and proposes an algorithm for parameter estimation. The experimental results revealed that the proposed method outperformed the baseline approaches.

本文言語English
ホスト出版物のタイトル2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings
編集者Naonori Ueda, Jen-Tzung Chien, Tomoko Matsui, Jan Larsen, Shinji Watanabe
出版社IEEE Computer Society
ページ1-6
ページ数6
ISBN(電子版)9781509063413
DOI
出版ステータスPublished - 2017 12月 5
外部発表はい
イベント2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Tokyo, Japan
継続期間: 2017 9月 252017 9月 28

出版物シリーズ

名前IEEE International Workshop on Machine Learning for Signal Processing, MLSP
2017-September
ISSN(印刷版)2161-0363
ISSN(電子版)2161-0371

Other

Other2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017
国/地域Japan
CityTokyo
Period17/9/2517/9/28

ASJC Scopus subject areas

  • 人間とコンピュータの相互作用
  • 信号処理

フィンガープリント

「Mel-Generalized cepstral regularization for discriminative non-negative matrix factorization」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