| Presentation | 2002/6/20 English pronunciation learning system utilizing speaker adaptation by Japanese speech Akinori Ito, Tadao Nagasawa, Motoyuki Suzuki, Shozo Makino, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper describes a computer-aided English learning system for Japanese speakers. The proposed system is composed of the following two subsystems: a pronunciation tutor to detect phoneme-level mispronunciations, and a prosody tutor which treats intonation and rhythm of the speech. The pronunciation tutor exploits VFS speaker adaptation technique to improve precision of phoneme labeling. On the adaptation, we developed a new adaptation scheme that used Japanese utterances to adapt English acoustic models. This method enables speaker adaptation for speakers who are not good at English pronunciation. The prosody tutor compares pitch pattern of native speakers' utterances and a student's one, and suggests how to improve intonation. In addition to intonation tutoring, the system compares duration of phrases between native speakers and a student. Evaluation experiments are carried out to compare native speakers' evaluation and the system's one against Japanese speakers' speech, and we obtained good correlation between the two evaluation, which shows that the proposed system can be as good teacher as native English speaker. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | language learning system / speaker adaptation / pronunciation learning / speech recognition |
| Paper # | SP2002-39 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2002/6/20(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) | English pronunciation learning system utilizing speaker adaptation by Japanese speech |
| Sub Title (in English) | |
| Keyword(1) | language learning system |
| Keyword(2) | speaker adaptation |
| Keyword(3) | pronunciation learning |
| Keyword(4) | speech recognition |
| 1st Author's Name | Akinori Ito |
| 1st Author's Affiliation | Graduage School of Engineering, Tohoku University() |
| 2nd Author's Name | Tadao Nagasawa |
| 2nd Author's Affiliation | Graduage School of Information Sciences, Tohoku University |
| 3rd Author's Name | Motoyuki Suzuki |
| 3rd Author's Affiliation | Graduage School of Engineering, Tohoku University |
| 4th Author's Name | Shozo Makino |
| 4th Author's Affiliation | Graduage School of Engineering, Tohoku University |
| Date | 2002/6/20 |
| Paper # | SP2002-39 |
| Volume (vol) | vol.102 |
| Number (no) | 159 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |