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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Divay, M., Vitale, A.J.: Algorithms for grapheme phoneme translation for English and French: Applications for database searches and speech synthesis. In: Computational Linguistics, vol. 23, pp. 495–523 (1997)
Davel, M., Barnard, E.: A default-and- refinement approach to pronunciation prediction. In: Proceedings of the 15th Annual Symposium of the Pattern Recognition Association of South Africa, pp. 119–123
Sejnowski, T.J., Rosenberg, C.R.: Parallel networks that learn to pronounce english text. Complex systems 1, 145–168 (1987)
Andersen, O., Kuhn, R., Lazarides, A.(eds.): Comparison of Two Tree-Structured Approaches for Grapheme-to-Phoneme Conversion. Proceedings of the International Conference on Spoken Language Processing, Philadelphia, USA, pp. 1808–1811 (1996)
Wang, W.-J., Hwang, S.-H., Chen, S.-H.: The broad study of homograph disambiguity for mandarin speech synthesis. In: Proceedings of the International Conference on Spoken Language Processing, Philadelphia, USA, vol. 3, pp. 1389–1392 (1996)
Yvon, F.: Grapheme-to-phoneme conversion using multiple unbounded overlapping chunks. In: Proceedings of Conference on New Methods in Natural Language Processing (NeMLaP), Ankara, Turkey, pp. 218–228 (1996)
Zhang, Z.-R., Chu, M.: An efficient way to learn rules for grapheme-to-phoneme conversion in Chinese. In: Processing of International Symposium on Chinese Spoken Language(ISCSLP 2002), p. 59 (2002)
Brill, E.: Transformation-based error-driven learning and natural language processing: A case study in part of speech tagging. Computational Linguistics 21(4), 543–565 (1995)
Yeh, A.S., Vilain, M.B.: Some Properties of Preposition and Subordinate Conjunction Attachments. In: 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Montreal, Canada, pp. 1436–1442 (1998)
Ferro, L., Vilain, M., Yeh, A.: Learning transformation rules to find grammatical relations. In: Workshop on Computational Natural Language Learning (GNLL 1999), pp. 43–52
Magerman, D.M.: Statistical decision-tree models for parsing. In: Proceedings of the 33rd Annual Meeting of the ACL, pp. 276–283 (1995)
Ma, X.J., Zhang, W.: Automatic Prosody Labeling Using both Text and Acoustic Information. In: Proc. ICASSP, HongKong (2003)
Kim, B., Lee, G.G.: Decision-Tree based Error Correction for Statistical Phrase Break Prediction in Korean. In: Proceedings of the 17th conference on Computational linguistic, pp. 1051–1055 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, M., Shi, Q., Zhang, W., Cai, L. (2005). Grapheme-to-Phoneme Conversion Based on a Fast TBL Algorithm in Mandarin TTS Systems. In: Wang, L., Jin, Y. (eds) Fuzzy Systems and Knowledge Discovery. FSKD 2005. Lecture Notes in Computer Science(), vol 3614. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11540007_74
Download citation
DOI: https://doi.org/10.1007/11540007_74
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28331-7
Online ISBN: 978-3-540-31828-6
eBook Packages: Computer ScienceComputer Science (R0)