Improving pronunciation by analogy for text-to-speech applications

This paper extends previous work on pronunciation by analogy (PbA) in several directions. PbA is a data-driven method for converting letters to sound, with potential application to next-generation text-to-speech systems. We experiment with a range of methods for matching letter patterns in input words to those in the system dictionary when building a pronunciation lattice. We give preliminary consideration to deriving lexical stress for input words. Common errors are analysed: these mostly involve vowel letters and phonemes. An output is not necessarily guaranteed in PbA { the so-called silence problem. We report on a simple but e ective strategy for silence avoidance. Finally, we introduce the idea of using di erent strategies in combination to improve performance.