Now showing items 1-4 of 4
A connectionist approach to speech recognition using peripheral auditory modelling
A prototype isolated word recogniser was constructed, with an auditory-based analysis component and a pattern classification module based on a parallel distributed processing paradigm. The auditory model used was a band-pass ...
Radial basis function network for speech pattern classification
A neural network model incorporating radial basis functions is used in a speech-pattern classification problem. The method is compared with a back-propagation neural network model and with a vector-quantised hidden Markov ...
Unstable connectionist networks in speech recognition
Connectionist networks evolve in time according to a prescribed rule. Typically, they are designed to be stable so that their temporal activity ceases after a short transient period. However, meaningful patterns in speech ...
Finite state machines from feature grammars
This paper describes the conversion of a set of feature grammar rules into a deterministic finite state machine that accepts the same language (or at least a well-defined related language).