A maximum entropy approach to Chinese grapheme-to-phoneme conversion

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Grapheme-to-phoneme (G2P) conversion plays an important role in speech synthesis. The main difficulty facing Chinese G2P conversion is that many Chinese characters are polyphonic, having more than one pronunciation. A Chinese G2P system must be able to pick the correct pronunciation from among several candidates. Contextual information on neighboring characters such as character n-grams, phonetic information, or position of the polyphone in a word or sentence is the key to correct prediction. Most previous works employed rule-based or rule-learning methods, which often suffered from data sparseness. In this paper, we propose a novel G2P approach to avoid data sparseness. Our method uses the maximum entropy (ME) model framework to represent contextual information as ME features. Our system achieves a top accuracy of 99.84%, which is significantly higher than other state-of-the-art rule-based and rule-learning methods. In addition, our approach consistently improves accuracy regardless of a character's main pronunciation ratio. Further analysis also shows that the ME model is fast and efficient, requiring much less training and labeling time.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Information Reuse and Integration, IRI 2009
Pages411-416
Number of pages6
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Information Reuse and Integration, IRI 2009 - Las Vegas, NV, United States
Duration: 10 Aug 200912 Aug 2009

Publication series

Name2009 IEEE International Conference on Information Reuse and Integration, IRI 2009

Conference

Conference2009 IEEE International Conference on Information Reuse and Integration, IRI 2009
Country/TerritoryUnited States
CityLas Vegas, NV
Period10/08/0912/08/09

Keywords

  • Chinese grapheme-to-phoneme conversion
  • Maximum entropy model
  • Speech synthesis

Fingerprint

Dive into the research topics of 'A maximum entropy approach to Chinese grapheme-to-phoneme conversion'. Together they form a unique fingerprint.

Cite this