Learnable Phonetic Representations in a Connectionist TTS System — II: Phonetics to Speech
In an earlier chapter, we described the overall structure of the SOMtalk text-to-speech system and detailed results suggesting that non-symbolic (‘phonetic’) representations — based on trajectories through a ‘phonetic’ space derived from a self-organising map — may play a useful part in deriving pronunciations from text. A similar strategy suggests itself for the subsequent stage in which synthetic speech is produced from the ‘phonetic’ representation. This makes it possible to bypass a symbolic ‘phonemic’ stage in the overall, trained system. In this case, only a small database has been used for learning because of the high computational cost of training on spectral data, but some encouraging preliminary results have been obtained.
KeywordsHunt Acoustics Diphone
Unable to display preview. Download preview PDF.