| Presentation | 2016-09-05 Acoustic event detection and removal using LSTM-CTC for speech recognition Yu Nasu, Hiroshi Fujimura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Deep learning techniques have drastically increased the speech recognition performance. However, there are few practical applications utilizing spontaneous speech recognition because of the difficulty compared to read speech recognition. Spontaneous speech is challenging to recognize due to various causes. In particular, acoustic events such as fillers and hesitation disfluencies can degrade speech recognition accuracy. In this paper, we propose a speech recognition system with simultaneous modeling of phonemes and acoustic events using an LSTM-CTC acoustic model, which efficiently detects or removes acoustic events in recognition outputs. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / acoustic modeling / LSTM / CTC / acoustic event detection |
| Paper # | PRMU2016-69,IBISML2016-24 |
| Date of Issue | 2016-08-29 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IPSJ-CVIM / IBISML |
|---|---|
| Conference Date | 2016/9/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / / Kenji Fukumizu(ISM) |
| Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.) |
| Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Nagoya Inst. of Tech.) |
| Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / / Toshihiro Kamishima(AIST) / Tomoharu Iwata(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media / Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Acoustic event detection and removal using LSTM-CTC for speech recognition |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | acoustic modeling |
| Keyword(3) | LSTM |
| Keyword(4) | CTC |
| Keyword(5) | acoustic event detection |
| 1st Author's Name | Yu Nasu |
| 1st Author's Affiliation | former Corporate Research and Development Center, Toshiba Corporation(former Toshiba) |
| 2nd Author's Name | Hiroshi Fujimura |
| 2nd Author's Affiliation | Corporate Research and Development Center, Toshiba Corporation(Toshiba) |
| Date | 2016-09-05 |
| Paper # | PRMU2016-69,IBISML2016-24 |
| Volume (vol) | vol.116 |
| Number (no) | PRMU-208,IBISML-209 |
| Page | pp.pp.121-126(PRMU), pp.121-126(IBISML), |
| #Pages | 6 |
| Date of Issue | 2016-08-29 (PRMU, IBISML) |