Presentation | 2021-03-05 Automatic music transcription system based on convolutional neural network for electric guitar considering sounds of same pitch and different strings Toshiaki Matsui, Tetsuya Matsumoto, Hiroaki Kudo, Yoshinori Takeuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this research, we propose a system that outputs tablature notation of an electric guitar performance from acoustic signals and tempo information. The user of the proposed system records only single note performances for all frets on each string as training data in advance. For training this system, we use single note data and chord data created by synthesis of the recorded single notes. We conducted an experiment using actual guitar performances. For monophonic guitar performances, we conducted a comparison experiment with a baseline method that can only estimate single tones combining pitch estimation and string classification. For monophonic guitar performances, the F-value of the proposed method were 0.988 for the pitch estimation and 0.844 for the fret and string position estimation. The proposed method resulted in a higher F-value than the baseline method in fret and string position estimation of monophonic performances. For polyphonic guitar performances, the F-value of the proposed method were 0.939 for the pitch estimation and 0.780 for the fret and string position estimation. The proposed method achieved a relatively high F-value without recording chord data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | automatic music transcription / convolutional neural network / electric guitar / tablature / string detection |
Paper # | PRMU2020-86 |
Date of Issue | 2021-02-25 (PRMU) |
Conference Information | |
Committee | PRMU / IPSJ-CVIM |
---|---|
Conference Date | 2021/3/4(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Computer Vision and Pattern Recognition for specific environment |
Chair | Yoichi Sato(Univ. of Tokyo) |
Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Automatic music transcription system based on convolutional neural network for electric guitar considering sounds of same pitch and different strings |
Sub Title (in English) | |
Keyword(1) | automatic music transcription |
Keyword(2) | convolutional neural network |
Keyword(3) | electric guitar |
Keyword(4) | tablature |
Keyword(5) | string detection |
1st Author's Name | Toshiaki Matsui |
1st Author's Affiliation | Nagoya University(Nagoya Univ) |
2nd Author's Name | Tetsuya Matsumoto |
2nd Author's Affiliation | Nagoya University(Nagoya Univ) |
3rd Author's Name | Hiroaki Kudo |
3rd Author's Affiliation | Nagoya University(Nagoya Univ) |
4th Author's Name | Yoshinori Takeuchi |
4th Author's Affiliation | Daido University(Daido Univ) |
Date | 2021-03-05 |
Paper # | PRMU2020-86 |
Volume (vol) | vol.120 |
Number (no) | PRMU-409 |
Page | pp.pp.97-102(PRMU), |
#Pages | 6 |
Date of Issue | 2021-02-25 (PRMU) |