共 13 条
- [11] VAINIO M, 2003, FINNISH SPEECH TECHN
- [12] Yamagishi J, 2008, INT CONF ACOUST SPEE, P3957
- [13] Yoshimura T., 2001, INTERSPEECH, P2263
Evaluation of Finnish Unit Selection and HMM-based Speech Synthesis
被引：0
作者：
Silen, Hanna
[1
]
Helander, Elina
[1
]
Nurminen, Jani
[2
]
Gabbouji, Moncef
[1
]
机构：
[1] Tampere Univ Technol, Dept Signal Proc, Tampere, Finland
[2] Nokia Devices R&D, Tampere, Finland
来源：
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5
|
2008年
基金：
芬兰科学院;
关键词：
speech synthesis;
unit selection;
hidden Markov models;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ;
0812 ;
0835 ;
1405 ;
摘要：
Unit selection and hidden Markov model (HMM) based synthesis have become the dominant techniques in text-to-speech (US) research. In this work, we combine HMM-based signal generation with the front end originally designed for unit selection based Finnish ITS and we evaluate the prosody of the output generated by the two synthesis techniques using the same speech database. Furthermore, we study the effect that the training set size has for the prosody and intelligibility in HMM-based synthesis. The results indicate that the HMM-based approach is capable of providing better prosody than unit selection even if the training set size is severely limited. The size of the training set, however, affects the prosodic quality and intelligibility of the HMM-based synthesizer.
引用
收藏
页码：1853 / +
页数：2
相关论文