Phan, T.S. and Dinh, A.T. and Vu, T.T. and Luong, C.M. (2014) An improvement of prosodic characteristics in Vietnamese text to speech system. In: 5th International Conference on Knowledge and Systems Engineering, KSE 2013, 17 October 2013 through 19 October 2013, Hanoi.
Full text not available from this repository. (Upload)Abstract
One important goal of TTS system is to generate natural-sounding synthesized voice. To meet the goal, a variety of tasks are performed to model the prosodic aspects of TTS voice. The task being discussed here is POS and Intonation tagging. The paper examines the effects of POS and Intonation information on the naturalness of a hiddenMarkov model (HMM) based speech when other resources are not available. It is discovered that, when a limited feature set is used for HMM context labels, the POS and Intonation tags improve the naturalness of the synthesized voice. © Springer International Publishing Switzerland 2014.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Divisions: | Faculties > Faculty of Information Technology |
| Identification Number: | 10.1007/978-3-319-02741-8_10 |
| Uncontrolled Keywords: | Computer programming; Computer science; Feature sets; Text-to-speech system; TTS systems; Vietnamese; Systems engineering |
| Additional Information: | Conference code: 102978. Language of original document: English. |
| URI: | http://eprints.lqdtu.edu.vn/id/eprint/10025 |
Actions (login required)
- View Item