| Presentation | 1993/6/18 Large-Vocabulary Spoken Word Recognition Using Different Pattern of a Posteriori Probability Jouji Miwa, Seiki Kon, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a method of large-vocabulary spoken word recognition using two kinds of different pattern of a posteriori probabiliety. These are outputs of first and second stage in the hierarchical network units of phoneme based on probability(H-NEUROPHONE).A likilihood of word for recognition is calculated by phoneme-based bottom-up and topdown processing.In the recognition experiment of 5240 words uttered by one adult male speaker,the recognition score using two kinds of pattern is 84.4% and 2.4% higher than one kind. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / large vocabulary / phoneme / top-down processing |
| Paper # | SP93-30 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 1993/6/18(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) | Large-Vocabulary Spoken Word Recognition Using Different Pattern of a Posteriori Probability |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | large vocabulary |
| Keyword(3) | phoneme |
| Keyword(4) | top-down processing |
| 1st Author's Name | Jouji Miwa |
| 1st Author's Affiliation | Faculty of Engineering,Iwate University() |
| 2nd Author's Name | Seiki Kon |
| 2nd Author's Affiliation | Faculty of Engineering,Iwate University |
| Date | 1993/6/18 |
| Paper # | SP93-30 |
| Volume (vol) | vol.93 |
| Number (no) | 88 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |