|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b10. 学術雑誌論文等 >
b10-1. 雑誌掲載論文 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/15477
|
| タイトル: | Weighted Robust Principal Component Analysis with Gammatone Auditory Filterbank for Singing Voice Separation |
| 著者: | Li, Feng
Akagi, Masato |
| キーワード: | Singing voice separation
Robust principal component analysis (RPCA)
Weighted
Gammatone auditory filterbank
Cochleagram
IBM/IRM estimation |
| 発行日: | 2017-10-26 |
| 出版者: | Springer |
| 誌名: | Lecture Notes in Computer Science |
| 巻: | 10639 |
| 開始ページ: | 849 |
| 終了ページ: | 858 |
| DOI: | 10.1007/978-3-319-70136-3_90 |
| 抄録: | This paper presents a proposed extension of robust principal component analysis (RPCA) with weighting (WRPCA) based on gammatone auditory filterbank for singing voice separation. Although the conventional RPCA is an effective method to separate singing voice and music accompaniment, it makes some strong assumptions. For example, drums may lie in the sparse subspace instead of being low-rank, which decreases the separation performance in many real-world applications, especially for drums existing in the mixture music signal. Accordingly, the proposed WRPCA method utilizes different weighted values between sparse (singing voice) and low-rank matrices (music accompaniment). In addition, we developed an extended RPCA on cochleagram using an alternative time-frequency (T-F) representation based on gammatone auditory filterbank. We also applied IBM/IRM estimation to improve the separation results. Evaluation results show that WRPCA achieves better separation performance than the conventional RPCA, especially for the IBM estimation method. |
| Rights: | This is the author-created version of Springer, Feng Li and Masato Akagi, Lecture Notes in Computer Science, 10639, 2017, 849-858. The original publication is available at www.springerlink.com, http://dx.doi.org/10.1007/978-3-319-70136-3_90 |
| URI: | http://hdl.handle.net/10119/15477 |
| 資料タイプ: | author |
| 出現コレクション: | b10-1. 雑誌掲載論文 (Journal Articles)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| 2749.pdf | | 292Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
