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. Copyright © 2014 International Speech Communication Association.
|Title of host publication||The 4th International Symposium on Tonal Aspects of Languages, Nijmegen, The Netherlands, May 13-16, 2014|
|Editors||C. GUSSENHOVEN, Y. CHEN, D. DEDIU|
|Place of Publication||Nijmegen|
|Publisher||International Speech Communication Association (ISCA)|
|Publication status||Published - 2014|
CitationLee, A., Xu, Y., & Prom-on, S. (2014). Modeling Japanese F₀ contours using the PENTAtrainers and AMtrainer. In C. Gussenhoven, Y. Chen, & D. Dediu (Eds.), The 4th International Symposium on Tonal Aspects of Languages, Nijmegen, The Netherlands, May 13-16, 2014 (pp. 164-167). Nijmegen: International Speech Communication Association (ISCA).
- AM theory
- PENTA model
- Pitch accent