Use of Multi-Layered Networks for Coding Speech with Phonetic Features

McGill University Montreal, Canada H3A2A7 PieroCosi Centro di Studio per Ie Ricerche di Fonetica, C.N.R., Via Oberdan,10, 35122 Padova, Italy ABSTRACT Preliminary results on speaker-independant speech recognition are reported. A method that combines expertise on neural networks with expertise on speech recognition is used to build the recognition systems. For transient sounds, eventdriven propertyextractors with variable resolution in the time and frequency domains are used. For sonorant speech, a model of the human auditory system is preferred to FFT as a front-end module. INTRODUCTION Combining a structural or knowledge-based approach for describing speech units with neural networks capable of automatically learning relations between acoustic properties and speech units is the research effort we are attempting.