Automatic Piano Music Transcription by Hadamard Product of Low-Rank NMF and CNN/CDAE Outputs

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2019/10/01

タイトル(英語): Automatic Piano Music Transcription by Hadamard Product of Low-Rank NMF and CNN/CDAE Outputs

著者名: Takeo Kawashima (Department of Electrical and Computer Engineering, Yokohama National University), Koichi Ichige (Department of Electrical and Computer Engineering, Yokohama National University)

著者名(英語): Takeo Kawashima (Department of Electrical and Computer Engineering, Yokohama National University), Koichi Ichige (Department of Electrical and Computer Engineering, Yokohama National University)

キーワード: automatic music transcription，convolutional neural network，non-negative matrix factorization

要約(英語): In this paper, we propose novel automatic piano music transcription methods which improve multi-pitch estimation accuracy. The conventional multi-pitch estimation method using low-rank non-negative matrix factorization (LR-NMF) cannot achieve a good accuracy because the method cannot detect true spectrum and analyze nonlinearity in sound. In the proposed method, the nonlinearity is analyzed using the convolutional neural network (CNN) or the convolutional denoising autoencoder (CDAE) as a post processing of LR-NMF. After the processing, we further improve the accuracy by the Hadamard product of the output from LR-NMF and that from CNN or CDAE. The performance of the proposed method is evaluated through computer simulation.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.139 No.10 （2019） 特集Ⅰ：インテリジェント・システム　特集Ⅱ：2018電気関係学会四国支部連合大会

本誌掲載ページ: 1106-1112 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/139/10/139_1106/_article/-char/ja/