ABSTRACT
2.1. Text Analysis
The aim of text analysis is to transform the input text into a sequence of phonetic symbols and to assign accent to utterance groups. All text analysis procedures deal with just symbols, not acoustical parameters. Because Japanese texts are written in a different manner from the European languages, some unique problems occur during text analysis. First of all, the Japanese writing system has both Chinese characters (Kanji) and Japanese syllabary (Kana), and most Kanji have several different readings. For example the character "https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9780429181610/0c21db12-68c2-4b42-9922-7d7f6845aa4f/content/images/1742-9994-3-18-1.jpg" xmlns:xlink="https://www.w3.org/1999/xlink"/>" has the following readings [Saito-92]:
