An efficient way to learn English grapheme-to-phoneme rules automatically
K. Torkkola · IEEE International Conference on Acoustics Speech and Signal Processing · 1993
An efficient way to learn automatically grapheme-to-phoneme mapping rules for English by using Kohonen's concept of dynamically expanding context is presented. This method constructs rules that are most general in the sense of an explicitly defined specificity hierarchy. As the hierarchy, the amount of expanding context around the symbol to be transformed, weighted towards the right, is used. To apply this concept to English text-to-speech mapping, the authors have used the 20008-word corpus provided in the public domain by T. Sejnowski and C.R. Rosenberg (Complex Syst. vol.1, no.1, p.145-68 of 1987), which was also used in the NETTALK experiments. Phoneme-level mapping accuracies of 91% with data not used in training demonstrate that the dynamically expanding context is able to capture quite efficiently the context-dependent relationships in the corpus.>