| Presentation | 2014-07-24 Investigation of Combining Multiple Language Modeling Techniques in Japanese Spontaneous Speech Recognition Ryo MASUMURA, Taichi ASAMI, Takanobu OBA, Hirokazu MASATAKI, Sumitaka SAKAUCHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recent large vocabulary speech recognition systems consist of two statistical models, the acoustic and language models. In acoustic modeling, deep neural networks have realized a breakthrough and significant performance improvements have been achieved. On the other hand, in language modeling, there have not been any reports of comparable improvements. Although it is clear that recent practical language models have several problems such as "locality", "task dependency" and "data sparseness", we cannot obtain significant performance improvements by solving these problems separately. In this paper, we try to use various language modeling techniques simultaneously to cover the entire problem. Our investigation is conducted by dividing language modeling techniques into three viewpoints, "one pass decoding", "unsupervised adaptation" and "rescoring". |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | language models / one pass decoding / unsupervised adaptation / rescoring |
| Paper # | SP2014-63 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2014/7/17(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Speech (SP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Investigation of Combining Multiple Language Modeling Techniques in Japanese Spontaneous Speech Recognition |
| Sub Title (in English) | |
| Keyword(1) | language models |
| Keyword(2) | one pass decoding |
| Keyword(3) | unsupervised adaptation |
| Keyword(4) | rescoring |
| 1st Author's Name | Ryo MASUMURA |
| 1st Author's Affiliation | NTT Media Intelligence Laboratories() |
| 2nd Author's Name | Taichi ASAMI |
| 2nd Author's Affiliation | NTT Media Intelligence Laboratories |
| 3rd Author's Name | Takanobu OBA |
| 3rd Author's Affiliation | NTT Media Intelligence Laboratories |
| 4th Author's Name | Hirokazu MASATAKI |
| 4th Author's Affiliation | NTT Media Intelligence Laboratories |
| 5th Author's Name | Sumitaka SAKAUCHI |
| 5th Author's Affiliation | NTT Media Intelligence Laboratories |
| Date | 2014-07-24 |
| Paper # | SP2014-63 |
| Volume (vol) | vol.114 |
| Number (no) | 151 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |