The aim of this project is to formulate a model of natural continuous speech that can quantify and distinguish between a) hardware constraints (articulatory, acoustic and perceptual) that have to be implemented in models of automatic speech technology, and b) language-specific constraints, or software constraints, that have to be learnt by the system. The model will be formulated on the basis of original data on coarticulatory effects in Spanish and English. The results of the model will allow to impose the software and hardware constraints of natural speech on automatic speech synthesis and recognition systems to achieve a better modelling of the system and to improve the quality of the results.
|Effective start/end date||12/12/90 → 12/12/93|
- Comisión Interministerial de Ciencia y Tecnología (CICYT): €48,790.16