| Presentation | 2018-03-20 DNN prefiltering for enhancement of voice recognition in noise environment Jun Takahashi, Kentaro Murase, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we applied convolutional denoising autoencoder (CDAE) as the prefilter of voice recognition and evaluated recognition accuracy of under the noise environoment such as BGM/environmental sound. To improve the voice recognition accuracy under the noise environment, prefilter requires not only noise reduction but also speech feature restoration. We trained CDAE which is the model that the noise signal converts into the speech signal. And, for restoration of speech features, we applied U-Net structure which connects same layer of multiple stacked autoencoder. Furthermore, considering further improvement of speech features, generative adversarial networks (GAN) are added to the model. We evaluated the voice recognition accuracy under the noise environment using prefilter that trained the voice of 20 people and 5 patterns of BGM/environmental sound. In the result, we confirmed that the speech recognition accuracy improved more than 10 points under the SNR 10dB. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Neural Network / Autoencoder / Voice recognition / Generative Adversarial Network / Denoising |
| Paper # | EA2017-170,SIP2017-179,SP2017-153 |
| Date of Issue | 2018-03-12 (EA, SIP, SP) |
| Conference Information | |
| Committee | SIP / EA / SP / MI |
|---|---|
| Conference Date | 2018/3/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Speech, Engineering/Electro Acoustics, Signal Processing, and Related Topics [SIP, EA, SP]/ Medical Image Engineering, Analysis, Recognition, etc. [MI] |
| Chair | Masahiro Okuda(Univ. of Kitakyushu) / Suehiro Shimauchi(NTT) / Yoichi Yamashita(Ritsumeikan Univ.) / Kensaku Mori(Nagoya Univ.) |
| Vice Chair | Shogo Muramatsu(Niigata Univ.) / Naoyuki Aikawa(TUS) / Mitsunori Mizumachi(Kyutech) / Hiroki Mori(Utsunomiya Univ.) / Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) |
| Secretary | Shogo Muramatsu(Chiba Inst. of Tech.) / Naoyuki Aikawa(Takushoku Univ.) / Mitsunori Mizumachi(Akita Pref. Univ.) / Hiroki Mori(Shizuoka Inst. of Science and Tech.) / Yoshiki Kawata(Shizuoka Univ.) / Yuichi Kimura(Meijo Univ.) |
| Assistant | Masayoshi Nakamoto(Hiroshima Univ.ひろ) / TREVINO Jorge(Tohoku Univ.) / Nobutaka Ito(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) / Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Signal Processing / Technical Committee on Engineering Acoustics / Technical Committee on Speech / Technical Committee on Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | DNN prefiltering for enhancement of voice recognition in noise environment |
| Sub Title (in English) | |
| Keyword(1) | Deep Neural Network |
| Keyword(2) | Autoencoder |
| Keyword(3) | Voice recognition |
| Keyword(4) | Generative Adversarial Network |
| Keyword(5) | Denoising |
| 1st Author's Name | Jun Takahashi |
| 1st Author's Affiliation | Fujitsu Laboratories LTD.(Fujitsu Labs.) |
| 2nd Author's Name | Kentaro Murase |
| 2nd Author's Affiliation | Fujitsu Laboratories LTD.(Fujitsu Labs.) |
| Date | 2018-03-20 |
| Paper # | EA2017-170,SIP2017-179,SP2017-153 |
| Volume (vol) | vol.117 |
| Number (no) | EA-515,SIP-516,SP-517 |
| Page | pp.pp.373-378(EA), pp.373-378(SIP), pp.373-378(SP), |
| #Pages | 6 |
| Date of Issue | 2018-03-12 (EA, SIP, SP) |