Tabtalk: reusability in data-oriented grapheme-to-phoneme conversion

In the traditional (knowledge-based) approach to the design of grapheme-to-phoneme modules in text-to-speech systems, it is claimed that various explicitly coded, language-speciic, linguistic knowledge sources are necessary for a good performance. Due to knowledge acquisition bottlenecks, this implies long development cycles. As an alternative, we propose to use inductive methods from machine learning in a simple combined Trie Search and Similarity-Based Reasoning approach and show that, for Dutch, its performance is better than that of the knowledge-based approach and backpropagation learning. Furthermore, we show that our approach is reusable for any language for which a training corpus exists.