Transliteration system for Arabic-Numeral Expressions using decision tree for intelligent Korean TTS

Though there has been much work on TTS technologies and several TTS systems have customized for Korean, current TTS systems output many errors in transliterating non-alphabetic symbols such as Arabic numerals and text symbols. Arabic Numeral Expressions (ANEs) show a high occurrence-frequency and deliver significant senses, especially in scientific or informative documents and texts. This paper proposes TAN (Transliteration system for Arabic-Numeral expressions) which can efficiently disambiguate the meaning and reading of Arabic Numeral Expressions in texts by using a decision tree. For the purpose of analyzing and learning data, three phases of learning elements were suggested: patterns of Arabic numerals combined with text symbols, contextual features and heuristic information were classified according to the senses and sounds of ANEs. Our corpus was made up of news articles issued from January 1st, 2000 to December 31SI, 2001 from 10 major newspapers in Korea. By learning the three phases of learning elements, the system shows 97.52% and 97.29% accuracies for the training set and the test set, respectively. This result shows that the accuracy of our system is 9.72% higher than that of a current TTS system for Korean.