| Presentation | 2017-03-02 Non-native speech conversion with consistency-aware recursive network and generative adversarial network Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Hiroyasu Ando, Kaoru Hiramatsu, Kunio Kashino, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper deals with the problem of automatically modifying the pronunciation of non-native speech. Since the pronunciation characteristics of non-native speakers tend to depend heavily on the context (such as words), conversion rules must be learned from and applied to a sequence of features rather than a single-frame feature. This paper proposes constructing a neural network that allows a sequence of features as an input and an output, and guarantees the consistency between the generated features within overlapping segments. We further propose applying a recently proposed generative adversarial network (GAN)-based post filterto the generated feature sequence with the aim of synthesizing natural sounding speech. Through subjective and quantitative evaluations, we confirmed the superiority of the proposed method over a conventional NN approach in terms of the conversion quality. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | EA2016-139,SIP2016-194,SP2016-134 |
| 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) | Non-native speech conversion with consistency-aware recursive network and generative adversarial network |
| Sub Title (in English) | |
| Keyword(1) | |
| Keyword(2) | |
| Keyword(3) | |
| Keyword(4) | |
| 1st Author's Name | Keisuke Oyamada |
| 1st Author's Affiliation | University of Tsukuba(Univ. of Tsukuba) |
| 2nd Author's Name | Hirokazu Kameoka |
| 2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 3rd Author's Name | Takuhiro Kaneko |
| 3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 4th Author's Name | Hiroyasu Ando |
| 4th Author's Affiliation | University of Tsukuba(Univ. of Tsukuba) |
| 5th Author's Name | Kaoru Hiramatsu |
| 5th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 6th Author's Name | Kunio Kashino |
| 6th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| Date | 2017-03-02 |
| Paper # | EA2016-139,SIP2016-194,SP2016-134 |
| Volume (vol) | vol.116 |
| Number (no) | EA-475,SIP-476,SP-477 |
| Page | pp.pp.315-320(EA), pp.315-320(SIP), pp.315-320(SP), |
| #Pages | 6 |
| Date of Issue | 2017-02-22 (EA, SIP, SP) |