File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Modeling Japanese F0 contours using the PENTAtrainers and AMtrainer
| Title | Modeling Japanese F0 contours using the PENTAtrainers and AMtrainer |
|---|---|
| Authors | |
| Issue Date | 2014 |
| Citation | The 4th International Symposium on Tonal Aspects of Languages (TAL 2014), Nijmegen, The Netherlands, 13-16 May 2014, p. 164-167 How to Cite? |
| Abstract | This study is a user report on modeling and predicting the F0 contour of Japanese utterances with PENTA Model and AM Theory. Through a 2640-word corpus of Japanese, the two models were compared using two versions of PENTAtrainer, as well as newly developed AMtrainer, respectively. The respective modelling and synthesis accuracies of different models are discussed with reference to the type of input they require. The satisfactory results achieved by these tools demonstrate their potential in offering a fair and direct comparison between the two models. We call for more collaborative effort in comparative modeling to achieve this goal. |
| Persistent Identifier | http://hdl.handle.net/10722/220583 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Lee, A | - |
| dc.contributor.author | Xu, Y | - |
| dc.date.accessioned | 2015-10-16T06:46:23Z | - |
| dc.date.available | 2015-10-16T06:46:23Z | - |
| dc.date.issued | 2014 | - |
| dc.identifier.citation | The 4th International Symposium on Tonal Aspects of Languages (TAL 2014), Nijmegen, The Netherlands, 13-16 May 2014, p. 164-167 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/220583 | - |
| dc.description.abstract | This study is a user report on modeling and predicting the F0 contour of Japanese utterances with PENTA Model and AM Theory. Through a 2640-word corpus of Japanese, the two models were compared using two versions of PENTAtrainer, as well as newly developed AMtrainer, respectively. The respective modelling and synthesis accuracies of different models are discussed with reference to the type of input they require. The satisfactory results achieved by these tools demonstrate their potential in offering a fair and direct comparison between the two models. We call for more collaborative effort in comparative modeling to achieve this goal. | - |
| dc.language | eng | - |
| dc.relation.ispartof | International Symposium on Tonal Aspects of Languages, TAL 2014 | - |
| dc.title | Modeling Japanese F0 contours using the PENTAtrainers and AMtrainer | - |
| dc.type | Conference_Paper | - |
| dc.identifier.email | Lee, A: albertlee@hku.hk | - |
| dc.identifier.authority | Lee, A=rp02091 | - |
| dc.identifier.hkuros | 250670 | - |
| dc.identifier.spage | 164 | - |
| dc.identifier.epage | 167 | - |