Presentation | 2017-03-01 Speech waveform synthesis based on WaveNet considering speech generation process Akira Tamamori, Tomoki Hayashi, Tomoki Toda, Kazuya Takeda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Our aim is to realize a new vocoder, which can resolve various constraints imposed on source-filter model and deal with speech waveform directly. In this study, we propose a method of synthesizing speech waveforms with WaveNet, which was a recently proposed neural network for generating audio signal waveforms, by using existing vocoder parameters as input auxiliary features. It is expected that these parameters are effective for auxiliary feature of waveform generation, because they are based on source-filter model. In the experiment, parameters of mel-cepstrum vocoder were selected as target, and quality of synthesized speech was objectively evaluated by SNR (Signal-to-Noise Ratio) and SDR (Signal-to-Distortion Ratio). From the results, it was confirmed that the sound quality was significantly improved for SNR and proposed method was effective. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | WaveNet / convolutional neural network / source-filter model / mel-cepstrum / fundamental frequency. / vocoder / deep leaning |
Paper # | EA2016-82,SIP2016-137,SP2016-77 |
Date of Issue | 2017-02-22 (EA, SIP, SP) |
Conference Information | |
Committee | SP / SIP / EA |
---|---|
Conference Date | 2017/3/1(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Industry Support Center |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Speech, Engineering/Electro Acoustics, Signal Processing, and Related Topics |
Chair | Kazunori Mano(Shibaura Inst. of Tech.) / Makoto Nakashizuka(Chiba Inst. of Tech.) / Mitsunori Mizumachi(Kyushu Inst. of Tech.) |
Vice Chair | Hiroki Mori(Utsunomiya Univ.) / Masahiro Okuda(Univ. of Kitakyushu) / Shogo Muramatsu(Niigata Univ.) / Yoichi Haneda(Univ. of Electro-Comm.) / Suehiro Shimauchi(NTT) |
Secretary | Hiroki Mori(Kobe Univ.) / Masahiro Okuda(Shizuoka Univ.) / Shogo Muramatsu(Ritsumeikan Univ.) / Yoichi Haneda(Chiba Inst. of Tech.) / Suehiro Shimauchi(KDDI R&D Labs.) |
Assistant | Taichi Asami(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Osamu Watanabe(Takushoku Univ.) / Shigeto Takeoka(Shizuoka Inst. of Science and Tech.) / TREVINO Jorge(Tohoku Univ.) |
Paper Information | |
Registration To | Technical Committee on Speech / Technical Committee on Signal Processing / Technical Committee on Engineering Acoustics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Speech waveform synthesis based on WaveNet considering speech generation process |
Sub Title (in English) | |
Keyword(1) | WaveNet |
Keyword(2) | convolutional neural network |
Keyword(3) | source-filter model |
Keyword(4) | mel-cepstrum |
Keyword(5) | fundamental frequency. |
Keyword(6) | vocoder |
Keyword(7) | deep leaning |
1st Author's Name | Akira Tamamori |
1st Author's Affiliation | Nagoya University/JST(Nagoya Univ.) |
2nd Author's Name | Tomoki Hayashi |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
3rd Author's Name | Tomoki Toda |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
4th Author's Name | Kazuya Takeda |
4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2017-03-01 |
Paper # | EA2016-82,SIP2016-137,SP2016-77 |
Volume (vol) | vol.116 |
Number (no) | EA-475,SIP-476,SP-477 |
Page | pp.pp.1-6(EA), pp.1-6(SIP), pp.1-6(SP), |
#Pages | 6 |
Date of Issue | 2017-02-22 (EA, SIP, SP) |