摘要
字音转换是德语语音合成系统不得不解决的难题。可以使用基于规则驱动的迭代有限状态转录机来解决这一问题。在该算法中,首先在一个词库的基础上制定一些字音转换规则,然后在此规则的基础上通过迭代有限状态转录机将德语单词中的所有字素转换成音素。经过对整个词库进行算法测试,单词的字音转换正确率可以达到94.4%。
It is difficult to convert graphemes to phonemes in German Speech Synthesis system.A rule-driven algorithm based on an iterated finite state transducer is proposed in present research to automatically convert graphemes to corresponding phonemes.In this algorithm,grapheme-to-phoneme rules are first made on the basis of a given lexicon;then graphemes of words are converted to phonemes following iterations resulting from morphological rules and phonological rules.Test results show that the accuracy of the total lexicon following application of the graphemes to phonemes conversion algorithm reaches as high as 94.4%.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第35期132-134,共3页
Computer Engineering and Applications
基金
国家社会科学基金项目资助No.08CYY001~~
关键词
德语语音合成
字音转换
有限状态转录机
German speech synthesis
grapheme-to-phoneme conversion
finite state transducer
