Accent Estimation of Japanese Words from Their Surfaces and Romanizations for Building Large Vocabulary Accent Dictionaries
This work addresses the need for improved accent dictionaries in Japanese TTS systems, particularly for compound words and proper nouns, though it is incremental as it builds on existing methods and data.
The authors tackled the problem of limited publicly available accent dictionaries for Japanese text-to-speech by developing an accent estimation technique that predicts word accents from surface and phonetic information, achieving high accuracies for certain word categories and creating a large vocabulary accent dictionary that outperforms UniDic in many cases.
In Japanese text-to-speech (TTS), it is necessary to add accent information to the input sentence. However, there are a limited number of publicly available accent dictionaries, and those dictionaries e.g. UniDic, do not contain many compound words, proper nouns, etc., which are required in a practical TTS system. In order to build a large scale accent dictionary that contains those words, the authors developed an accent estimation technique that predicts the accent of a word from its limited information, namely the surface (e.g. kanji) and the yomi (simplified phonetic information). It is experimentally shown that the technique can estimate accents with high accuracies, especially for some categories of words. The authors applied this technique to an existing large vocabulary Japanese dictionary NEologd, and obtained a large vocabulary Japanese accent dictionary. Many cases have been observed in which the use of this dictionary yields more appropriate phonetic information than UniDic.