Paper: Modeling Letter-to-Phoneme Conversion as a Phrase Based Statistical Machine Translation Problem with Minimum Error Rate Training

ACL ID N09-3016
Title Modeling Letter-to-Phoneme Conversion as a Phrase Based Statistical Machine Translation Problem with Minimum Error Rate Training
Venue HLT-NAACL Companion Volume: Student Research Workshop and Doctoral Consortium
Session
Year 2009
Authors

Letter-to-phonemeconversionplaysanimpor- tantroleinseveralapplications. Itcanbeadif- ficulttaskbecausethemappingfromlettersto phonemescanbemany-to-many. Wepresenta language independent letter-to-phoneme con- version approach which is based on the pop- ular phrase based Statistical Machine Trans- lation techniques. The results of our ex- periments clearly demonstrate that such tech- niques can be used effectively for letter-to- phoneme conversion. Our results show an overall improvement of 5.8% over the base- line and are comparable to the state of the art. Wealsoproposeameasuretoestimatethedif- ficulty level of L2P taskforalanguage.