Abstract | ||
---|---|---|
This paper introduces a Syllable HMM based Mandarin ITS system. 10-state left-to-right HMMs are used to model each syllable. We leverage the corpus and the front end of a concatenative TTS system to build the Syllable HMM based TTS system. Furthermore, we utilize the unique consonant/vowel structure of Mandarin syllable to improve the voiced/unvoiced decision of HMM states. Evaluation results show that the Syllable HMM based Mandarin TTS system with a 5.3MB's model size can achieve an overall quality close to a concatenative ITS system with 1GB' data size. |
Year | Venue | Keywords |
---|---|---|
2009 | INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | Mandarin, syllable, HMM, TTS, synthesis |
Field | DocType | Citations |
Computer science,Speech recognition,Syllable,Hidden Markov model,Mandarin Chinese | Conference | 3 |
PageRank | References | Authors |
0.67 | 1 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiwei Shuang | 1 | 42 | 6.83 |
Shiyin Kang | 2 | 150 | 15.05 |
Qin Shi | 3 | 61 | 10.77 |
Yong Qin | 4 | 161 | 42.54 |
Lian-Hong Cai | 5 | 657 | 67.66 |