INTERSPEECH 2004 - ICSLP
Modern Japanese texts often include Western sourced words written in the Roman alphabet. Even Japanese sourced words are sometimes transliterated into the Roman alphabet. As most of them are very new and idiosyncratic proper nouns, it is impractical to assume all those alphabetic words can be registered in the word dictionary of a text-to-speech system; their pronunciation must be derived automatically. As long vowel expressions are the same with short vowel or diphthong expressions in Japanese words transliterated into the alphabet, long vowel detection is necessary for generating highly accurate pronunciation. This paper proposes a method to detect long vowel positions using the Support Vector Machine. The cost of making the learning model for the detection is very low because the training data can be generated automatically from the text-to-speech word dictionary. 93.2% word accuracy was achieved which is almost the maximum accuracy possible from just spelling information.
Bibliographic reference. Hisako, Asano / Hideharu, Nakajima / Hideyuki, Mizuno / Masahiro, Oku (2004): "Long vowel detection for letter-to-sound conversion for Japanese sourced words transliterated into the alphabet", In INTERSPEECH-2004, 1917-1920.