| Presentation | 2017-12-21 ［ポスター講演］LSTMを用いた音響信号からの擬音語生成 Shota Ikawa, Kunio Kashino, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Representing various acoustic events by natural language seems to play an important role in natural man-machine communication, retrieval of multimedia database, detection of abnormal sound. In this paper, we propose a new method to generate onomatopoeia from acoustic signals. In the conventional onomatopoeia generation method, a method of classifying an input signal into classes presumed in advance or subdividing it into segments corresponding to phonemes was studied, but it was difficult to deal with unknown sounds and to segment the signal in units of phonemes. The proposed method is based on the Sequence-to-Sequence framework, It automatically generates onomatopoeia in End-to-End. Experiment showed that the mean phoneme error rate (MPER) was 2.8% and the word error rate (WER) was 7.2%, indicating that it is possible to realize a lower error rate than the conventional method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Acoustic signal processing / Environmental sound / Onomatopoeia / Sequence-to-Sequence |
| Paper # | SP2017-58 |
| Date of Issue | 2017-12-14 (SP) |
| Conference Information | |
| Committee | NLC / IPSJ-NL / SP / IPSJ-SLP |
|---|---|
| Conference Date | 2017/12/20(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Waseda Univ. Green Computing Systems Research Organization |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | The 4th Natural Language Processing Symposium & The 19th Spoken Language Symposium |
| Chair | Hiroshi Kanayama(IBM) / Kentaro Inui(Tohoku Univ.) / Yoichi Yamashita(Ritsumeikan Univ.) / Nobuaki Minematsu(Univ. Tokyo) |
| Vice Chair | Takeshi Sakaki(Hottolink) / Kazutaka Shimada(Kyushu Inst. of Tech.) / / Hiroki Mori(Utsunomiya Univ.) |
| Secretary | Takeshi Sakaki(Ryukoku Univ.) / Kazutaka Shimada(NTT) / (Osaka Univ.) / Hiroki Mori(Tokyo Inst. of Tech.) / (Mixi Co. Ltd.) |
| Assistant | Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Takeshi Kobayakawa(NICT) / / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / Technical Committee on Speech / Special Interest Group on Spoken Language Processing |
|---|---|
| Language | JPN-ONLY |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | |
| Sub Title (in English) | |
| Keyword(1) | Acoustic signal processing |
| Keyword(2) | Environmental sound |
| Keyword(3) | Onomatopoeia |
| Keyword(4) | Sequence-to-Sequence |
| 1st Author's Name | Shota Ikawa |
| 1st Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
| 2nd Author's Name | Kunio Kashino |
| 2nd Author's Affiliation | The University of Tokyo(Univ. Tokyo/NTT) |
| Date | 2017-12-21 |
| Paper # | SP2017-58 |
| Volume (vol) | vol.117 |
| Number (no) | SP-368 |
| Page | pp.pp.17-20(SP), |
| #Pages | 4 |
| Date of Issue | 2017-12-14 (SP) |