| Presentation | 2022-11-29 Density Ratio Approach-based multiple Encoder-Decoder ASR model integration Keigo Hojo, Daiki Mori, Yukoh Wakabayashi, Atsunori Ogawa, Norihide Kitaoka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | One of the methods to improve the performance of Encoder--Decoder speech recognition is the integration of an ASR models and a language model. Based on the Density Ratio Approach, we propose a method to build an ASR system by integrating multiple ASR models and combining them with an external language models. The proposed method enables speech recognition use a variety of acoustic information and linguistic information that has not been learned by the ASR models. Experimental results show that the proposed method is more accurate than conventional integration methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Multiple ASR model / Integration of acoustic information / Language model replacement / Density Ratio Approach |
| Paper # | NLC2022-10,SP2022-30 |
| Date of Issue | 2022-11-22 (NLC, SP) |
| Conference Information | |
| Committee | NLC / IPSJ-NL / SP / IPSJ-SLP |
|---|---|
| Conference Date | 2022/11/29(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Mitsuo Yoshida(Univ. of Tsukuba) / 須藤 克仁(奈良先端科学技術大学院大学) / Tomoki Toda(Nagoya Univ.) / 戸田 智基(名古屋大学) |
| Vice Chair | Hiroki Sakaji(Univ. of Tokyo) / Takeshi Kobayakawa(NHK) |
| Secretary | Hiroki Sakaji(NTT) / Takeshi Kobayakawa(Hiroshima Univ. of Economics) / (株式会社デンソーアイティーラボラトリ) / (北海学園大学) / (東京農工大学) |
| Assistant | Kanjin Takahashi(Sansan) / Yasuhiro Ogawa(Nagoya Univ.) / / Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo) |
| 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 |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Density Ratio Approach-based multiple Encoder-Decoder ASR model integration |
| Sub Title (in English) | |
| Keyword(1) | Multiple ASR model |
| Keyword(2) | Integration of acoustic information |
| Keyword(3) | Language model replacement |
| Keyword(4) | Density Ratio Approach |
| 1st Author's Name | Keigo Hojo |
| 1st Author's Affiliation | Toyohashi University of Technology(TUT) |
| 2nd Author's Name | Daiki Mori |
| 2nd Author's Affiliation | Toyohashi University of Technology(TUT) |
| 3rd Author's Name | Yukoh Wakabayashi |
| 3rd Author's Affiliation | Toyohashi University of Technology(TUT) |
| 4th Author's Name | Atsunori Ogawa |
| 4th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
| 5th Author's Name | Norihide Kitaoka |
| 5th Author's Affiliation | Toyohashi University of Technology(TUT) |
| Date | 2022-11-29 |
| Paper # | NLC2022-10,SP2022-30 |
| Volume (vol) | vol.122 |
| Number (no) | NLC-287,SP-288 |
| Page | pp.pp.5-9(NLC), pp.5-9(SP), |
| #Pages | 5 |
| Date of Issue | 2022-11-22 (NLC, SP) |