Abstract | ||
---|---|---|
This paper describes a Japanese dictation system that uses a stochastic language model based on sequences of Japanese characters. The trigram probabilities, which are obtained from a text database consisting of Kanji and Kana, are used to construct a source model. A Japanese dictation system generally requires Kana-to-Kanji conversion if the system uses a phoneme based unit for the acoustic processing. However, a system that uses a Kanji-and-Kana character source model can generate an output Kanji-and Kana sequence directly from input speech without using Kana-to-Kanji conversion. The system is tested using 274 phrases uttered by one male speaker, and achieves 58.4% phrase transcription rate. When the system uses a pronunciation dictionary and eliminates the candidates whose Kanji readings are contextually inappropriate, the phrase transcription rate increases to 63.9%. It is confirmed that a Japanese character source model is efficient for a Japanese dictation system. |
Year | DOI | Venue |
---|---|---|
1992 | 10.1109/ICASSP.1992.225978 | ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1 |
Keywords | DocType | Volume |
dictation,speech recognition,Japanese dictation system,Kana,Kanji,character source modeling,phrase transcription rate,pronunciation dictionary,speech recognition,stochastic language model,test-set perplexity,text database,trigram probabilities | Conference | 1 |
ISBN | Citations | PageRank |
0-7803-0532-9 | 1 | 0.41 |
References | Authors | |
4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tomokazu Yamada | 1 | 13 | 5.00 |
Shouichi Matsunaga | 2 | 1 | 0.41 |
Kiyohiro Shikano | 3 | 2662 | 928.81 |