| Presentation | 2000/2/18 Estimation of Vocal Tract Shape Using A-b-S Method by Articulatory-Acoustic Transformation for Spoken Language Learning. Takashi Hirano, Jouji Miwa, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper describes an estimation system of the vocal tract shape using A-b-S(Analysis-by-Synthesis) methods for computer assisted spoken language learning(CALL). In the snalysis stage of the method, learner's formant frequencies are extracted. In the synthesis stage, 11 parameters such as places and areas of articulation are used as a model of vocal tract shape, initial value of known phoneme is set typical value required from the MRI data, and synthesized parameters are calculated with articulatory-acoustic transformation. In the last stage, the vocal tract shape is estimated with minimum error function. An estimation experiment is carried out for real English speech uttered by a native speaker such as / la / and / ala / which are difficult to pronounce for Japanese. From the experiment, the dynamic vocal tract shape is correctly estimated and the effectiveness was confirmed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Spoken language learning / Estimation of vocal tract shape / Articulatory-acoustic transformation / Analysis by synthesis / 11 dimensional vocal tract method / Typical value |
| Paper # | SP99-154 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2000/2/18(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) | Estimation of Vocal Tract Shape Using A-b-S Method by Articulatory-Acoustic Transformation for Spoken Language Learning. |
| Sub Title (in English) | |
| Keyword(1) | Spoken language learning |
| Keyword(2) | Estimation of vocal tract shape |
| Keyword(3) | Articulatory-acoustic transformation |
| Keyword(4) | Analysis by synthesis |
| Keyword(5) | 11 dimensional vocal tract method |
| Keyword(6) | Typical value |
| 1st Author's Name | Takashi Hirano |
| 1st Author's Affiliation | Department of Computer and Information Science, Faculty of Engineering, Iwate University() |
| 2nd Author's Name | Jouji Miwa |
| 2nd Author's Affiliation | Department of Computer and Information Science, Faculty of Engineering, Iwate University |
| Date | 2000/2/18 |
| Paper # | SP99-154 |
| Volume (vol) | vol.99 |
| Number (no) | 627 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |