- Abstract:
-
This paper describes a new training method of average voice model for speech synthesis in which arbitrary speaker's voice is generated based on speaker adaptation. When the amount of training data is limited, the distributions of average voice model often have bias depending on speaker and/or gender and this will degrade the quality of synthetic speech. In the proposed method, to reduce the influence of speaker dependence, we incorporate a context clustering technique called shared decision tree context clustering and speaker adaptive training into the training procedure of average voice model. From the results of subjective tests, we show that the average voice model trained using the proposed method generates more natural sounding speech than the conventional average voice model. Moreover, it is shown that voice characteristics and prosodic features of synthetic speech generated from the adapted model using the proposed method are closer to the target speaker than the conventional method.
- Links To Paper
- IEICE
- Bibtex format
- @Article{EDI-INF-RR-1028,
- author = {
Junichi Yamagishi
and Masatsune Tamura
and Takashi Masuko
and Keiichi Tokuda
and Takao Kobayashi
},
- title = {A Training Method of Average Voice Model for HMM-based Speech Synthesis},
- journal = {IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences},
- publisher = {Oxford University Press},
- year = 2003,
- month = {Aug},
- volume = {E86-A},
- pages = {1956-1963},
- url = {http://search.ieice.org/bin/summary.php?id=e86-a_8_1956&category=A&lang=E&year=2003&abst=&auth=1},
- }
|
