Presentation | 2020-03-02 [Poster Presentation] High-precision modeling of distortion stomp box by deep learning using spectral features Kento Yoshimoto, Daichi Kitahara, Akira Hirabayashi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a method for modeling distortion stomp box with high accuracy using a deep neural network, WaveNet. The conventional method using the WaveNet adopted the error-to-signal ratio (ESR) defined in time domain as the loss function. Then, the high-frequency components were not sufficiently reproduced. To reproduce more accurate high-frequency components, we modify the loss function by adding the error of the spectral feature. We use a short-time Fourier transform and a mel frequency spectrogram as the spectral feature. Numerical experiments using an Ibanez SD9 show that the proposed method can generate modeling sounds with more accurate high-frequency components. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Distortion stomp box / black-box modeling / WaveNet / loss function / spectral features |
Paper # | EA2019-124,SIP2019-126,SP2019-73 |
Date of Issue | 2020-02-24 (EA, SIP, SP) |
Conference Information | |
Committee | SP / EA / SIP |
---|---|
Conference Date | 2020/3/2(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Industry Support Center |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hisashi Kawai(NICT) / Kenichi Furuya(Oita Univ.) / Naoyuki Aikawa(TUS) |
Vice Chair | Akinobu Ri(Nagoya Inst. of Tech.) / Suehiro Shimauchi(Kanazawa Inst. of Tech.) / Shigeto Takeoka(Shizuoka Inst. of Science and Tech.) / Kazunori Hayashi(Osaka City Univ) / Yukihiro Bandou(NTT) |
Secretary | Akinobu Ri(Kyoto Univ.) / Suehiro Shimauchi(Waseda Univ.) / Shigeto Takeoka(NHK) / Kazunori Hayashi(Univ. of Tokyo) / Yukihiro Bandou(Hiroshima Univ.) |
Assistant | Tomoki Koriyama(Univ. of Tokyo) / Yusuke Ijima(NTT) / Keisuke Imoto(Ritsumeikan Univ.) / Daisuke Morikawa(Toyama Pref Univ.) / Kenjiro Sugimoto(Waseda Univ.) |
Paper Information | |
Registration To | Technical Committee on Speech / Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] High-precision modeling of distortion stomp box by deep learning using spectral features |
Sub Title (in English) | |
Keyword(1) | Distortion stomp box |
Keyword(2) | black-box modeling |
Keyword(3) | WaveNet |
Keyword(4) | loss function |
Keyword(5) | spectral features |
1st Author's Name | Kento Yoshimoto |
1st Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
2nd Author's Name | Daichi Kitahara |
2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
3rd Author's Name | Akira Hirabayashi |
3rd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
Date | 2020-03-02 |
Paper # | EA2019-124,SIP2019-126,SP2019-73 |
Volume (vol) | vol.119 |
Number (no) | EA-439,SIP-440,SP-441 |
Page | pp.pp.135-140(EA), pp.135-140(SIP), pp.135-140(SP), |
#Pages | 6 |
Date of Issue | 2020-02-24 (EA, SIP, SP) |