Supervised nonnegative matrix factorization with Dual-Itakura-Saito and Kullback-Leibler divergences for music transcription

Hideaki Kagami, Masahiro Yukawa

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

In this paper, we present a convex-analytic approach to supervised nonnegative matrix factorization (SNMF) based on the Dual-Itakura-Saito (Dual-IS) and Kullback-Leibler (KL) divergences for music transcription. The Dual-IS and KL divergences define convex fidelity functions, whereas the IS divergence defines a nonconvex one. The SNMF problem is formulated as minimizing the divergence-based fidelity function penalized by the ℓ1 and row-block ℓ1 norms subject to the nonnegativity constraint. Simulation results show that (i) the use of the Dual-IS and KL divergences yields better performance than the squared Euclidean distance and that (ii) the use of the Dual-IS divergence prevents from false alarms efficiently.

本文言語English
ホスト出版物のタイトル2016 24th European Signal Processing Conference, EUSIPCO 2016
出版社European Signal Processing Conference, EUSIPCO
ページ1138-1142
ページ数5
ISBN(電子版)9780992862657
DOI
出版ステータスPublished - 2016 11月 28
イベント24th European Signal Processing Conference, EUSIPCO 2016 - Budapest, Hungary
継続期間: 2016 8月 282016 9月 2

出版物シリーズ

名前European Signal Processing Conference
2016-November
ISSN(印刷版)2219-5491

Other

Other24th European Signal Processing Conference, EUSIPCO 2016
国/地域Hungary
CityBudapest
Period16/8/2816/9/2

ASJC Scopus subject areas

  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Supervised nonnegative matrix factorization with Dual-Itakura-Saito and Kullback-Leibler divergences for music transcription」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