Abstract
This paper focuses on integrated prosodie word prediction for Chinese TTS, To avoid the problem of inconsistency between lexical words and prosodie words in Chinese, lexical word segmentation and prosodie word prediction are taken as one process instead of two independent tasks. Furthermore, two word-based approaches are proposed to drive this integrated prosodie word prediction: The first one follows the notion of lexicalized hidden Markov models, and the second one is borrowed from unknown word identification for Chinese. The results of our primary experiment show these integrated approaches are effective.
Original language | English |
---|---|
Title of host publication | NLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings |
Editors | Chengqing Zong |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 413-418 |
Number of pages | 6 |
ISBN (Electronic) | 0780379020, 9780780379022 |
DOIs | |
Publication status | Published - 2003 |
Externally published | Yes |
Event | International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003 - Beijing, China Duration: Oct 26 2003 → Oct 29 2003 |
Publication series
Name | NLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings |
---|
Conference
Conference | International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003 |
---|---|
Country/Territory | China |
City | Beijing |
Period | 10/26/03 → 10/29/03 |
Bibliographical note
Publisher Copyright:© 2003 IEEE.
ASJC Scopus Subject Areas
- Artificial Intelligence
- Computational Theory and Mathematics
- Software
Keywords
- Lexicalized HMMs
- Prosodie word prediction
- Text-to-speech synthesis