From text to speech: the MITalk system
From text to speech: the MITalk system
The 'Neural' Phonetic Typewriter
Computer
Self-organization and associative memory: 3rd edition
Self-organization and associative memory: 3rd edition
Data-oriented methods for grapheme-to-phoneme conversion
EACL '93 Proceedings of the sixth conference on European chapter of the Association for Computational Linguistics
| Hi-index | 0.00 |
The goal of the research presented here is to apply unsupervised neural network learning methods to some of the lower-level problems in speech synthesis currently performed by rule-based systems. The latter tend to be strongly influenced by notations developed by linguists (see figure 1 in Klatt (1987)), which were primarily devised to deal with written rather than spoken language. In general terms, what is needed in phonetics is a notation that captures information about ratios rather than absolute values, as is typically seen in biological systems. The notations derived here are based on an ordered pattern space that can be dealt with more easily by neural networks, and by systems involving a neural and symbolic component. Hence, the approach described here might also be useful in the design of a hybrid neural/symbolic system to operate in the speech synthesis domain.