Grapheme-to-phoneme conversion based on a fast TBL algorithm in mandarin TTS systems

Authors:
Min Zheng;Qin Shi;Wei Zhang;Lianhong Cai
Affiliations:
Computer Science Department in Tsinghua University, Beijing, China;IBM China Research Lab, Beijing, China;IBM China Research Lab, Beijing, China;Computer Science Department in Tsinghua University, Beijing, China
Venue:
FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part II
Year:
2005

Citing 5
Cited 0

Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging

Computational Linguistics
Algorithms for grapheme-phoneme translation for English and French: applications for database searches and speech synthesis

Computational Linguistics
Some properties of preposition and subordinate conjunction attachments

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Statistical decision-tree models for parsing

ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Decision-tree based error correction for statistical phrase break prediction in Korean

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

Grapheme-to-phoneme (G2P) conversion is an important subcomponent in many speech processing systems. The difficulty in Chinese G2P conversion is to pick out one correct pronunciation from several candidates according to the context information such as part-of-speech, lexical words, length of the word, or position of the polyphone in a word or a sentence. By evaluating the distribution of polyphones in a large text corpus with correct pinyin transcriptions, this paper points out that correct G2P conversion for 78 key polyphones greatly decrease the overall error rate. This paper proposed a fast Transformation-based error-driven learning (TBL) algorithm to solve G2P conversion. The correct rates of polyphones, which originally have high accuracy or low accuracy, are both improved. After compared with Decision Tree algorithm, TBL algorithm shows better performance to solve the polyphone problem.