Language-independent Grapheme-phoneme Conversion and Word Stress Assignment as a Web Service

We introduce a new language-independent procedure for grapheme-phoneme conversion, syllabification, and word stress assignment. Grapheme-phoneme conversion and syllabification is carried out by means of fallback sequences of decision trees trained on varying context sizes. Word stress is determined within an analogy-based framework by means of a Bayes classifier. Evaluation results on six languages are presented. Furthermore, it is described, how the tool is implemented and to be accessed as a web service that is freely available for academic research.