DocumentCode :
3425275
Title :
Tree-guided transformation-based homograph disambiguation in Mandarin TTS system
Author :
Liu, Fangzhou ; Shi, Qin ; Tao, Jianhua
Author_Institution :
Inst. of Autom., Chinese Acad. of Sci., Beijing
fYear :
2008
fDate :
March 31 2008-April 4 2008
Firstpage :
4657
Lastpage :
4660
Abstract :
Homograph disambiguation is the core issue of the grapheme- to-phoneme conversion in Mandarin Text-to-Speech system. In this paper, a hybrid algorithm called tree-guided transformation-based learning (TTBL), which combines decision tree with transformation-based learning (TBL), is proposed to resolve homograph ambiguity. It can automatically generate templates, thereby avoiding manually summarizing templates, which is time-consuming and laborious in conventional TBL. In addition, the paper evaluates various keyword selection approaches in different domains. Results of comparative experiments show that, for the task of homograph disambiguation, templates automatically generated by decision tree achieve comparable performance to manually summarized templates, and the TTBL significantly outperforms decision tree.
Keywords :
decision trees; learning (artificial intelligence); natural language processing; speech synthesis; Mandarin text-to-speech system; decision tree template; grapheme- to-phoneme conversion; homograph disambiguation; keyword selection approach; tree-guided transformation-based learning; Automation; Decision trees; Error correction; Laboratories; Machine learning algorithms; Pattern recognition; Speech synthesis; Stochastic processes; Training data; Tree graphs; decision tree; graphemeto-phoneme; homograph disambiguation; transformation-based learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
ISSN :
1520-6149
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2008.4518695
Filename :
4518695
Link To Document :
بازگشت