Paper Info
Title
KANJI-TO-HIRAGANA CONVERSION BASED ON A LANGUAGE MODEL
Abstract
In speech recognition systems, a common problem is tran- scription of new additions to the recognition lexicon into their phonetic symbols. Specificto the Japanese language, such a problem can be dealt with in two steps. In this paper, we focus on the firststep, in which the new lexical entry is converted into a set of hiragana syllabaries, which is almost a phonetic transcription. We propose a conversion scheme which yields the most likely hiragana syllabaries, based on a language model. Results from our evaluations on three test sets are also reported. Although the study is conducted on Japanese only, our approach has applications to Chinese.
Year
DOI
Venue
2001
10.1109/ICASSP.2001.940899
ICASSP
Keywords
Field
DocType
speech recognition,probability,white spaces,japanese language,statistical analysis,automatic speech recognition,language model,natural languages,dictionaries,writing,chinese,testing
Hiragana,Phonetic transcription,Lexical item,Computer science,Japanese language,Speech recognition,Lexicon,Natural language,Artificial intelligence,Natural language processing,Language model,Kanji
Conference
Citations 
PageRank 
References 
0
0.34
2
Authors
1
Name
Order
Citations
PageRank
Wei-Bin Chang151.63