| Presentation | 2015-01-22 Automatic prediction of intelligibility of English words spoken with Japanese accents : Comparative study of features and models used for prediction Teeraphon PONGKITTIPHAN, Nobuaki MINEMATSU, Takehiko MAKINO, Daisuke SAITO, Keikichi HIROSE, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This study investigates automatic prediction of the words in given sentences that will be unintelligible to American listeners when they are pronounced with Japanese accents. The ERJ intelligibility database contains results of a large listening test, where 800 English sentences read with Japanese accents were presented to 173 American listeners and correct perception rate was obtained for each spoken word. By using this database, in our previous study, an intelligibility predictor was built for each word of input texts or utterances. For prediction, lexical and linguistic features were extracted from texts and pronunciation distance and word confusability were calculated from utterances. CART was used as prediction model. In this paper, new features that are related to speech prosody and three new prediction models of ensemble methods (Adaboost, Random Forest and Extremely Randomized Trees) are tested and compared to the old features and model. Finally, our new system can predict very unintelligible and rather unintelligible words with F1-scores of 72.74% and 84.78%, respectively. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | spoken word intelligibility / ERJ database / prosodic features / machine learning / IPA / L2 learning / foreign accent |
| Paper # | SP2014-132 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2015/1/15(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 | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic prediction of intelligibility of English words spoken with Japanese accents : Comparative study of features and models used for prediction |
| Sub Title (in English) | |
| Keyword(1) | spoken word intelligibility |
| Keyword(2) | ERJ database |
| Keyword(3) | prosodic features |
| Keyword(4) | machine learning |
| Keyword(5) | IPA |
| Keyword(6) | L2 learning |
| Keyword(7) | foreign accent |
| 1st Author's Name | Teeraphon PONGKITTIPHAN |
| 1st Author's Affiliation | Faculty of Engineering, The University of Tokyo() |
| 2nd Author's Name | Nobuaki MINEMATSU |
| 2nd Author's Affiliation | Faculty of Engineering, The University of Tokyo |
| 3rd Author's Name | Takehiko MAKINO |
| 3rd Author's Affiliation | Faculty of Economics, Chuo University |
| 4th Author's Name | Daisuke SAITO |
| 4th Author's Affiliation | Faculty of Engineering, The University of Tokyo |
| 5th Author's Name | Keikichi HIROSE |
| 5th Author's Affiliation | Faculty of Engineering, The University of Tokyo |
| Date | 2015-01-22 |
| Paper # | SP2014-132 |
| Volume (vol) | vol.114 |
| Number (no) | 411 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |