SPIKE-V: AN ADAPTIVE MECHANISM FOR SPEECH-RATE INDEPENDENT TIMING
Sean McLennan, Steve Hockema · Indiana Magazine of History (Indiana University) · 2004
A neuronal model intended to target highly sonorant periods of a speech stream is presented. The model—“Spike-V”—uses habituation and Hebbian learning in opposition to each other to dynamically adjust its behavior. Acting in realtime, driven by only the signal, Spike-V produces a spike-train in which each spike corresponds to roughly the center of a period of high sonority (i.e. a vowel) in the input. The model adapts robustly and rapidly to changes in the speech stream providing an implicit, realtime measure of speaking rate that could be useful in connectionist models of speech recognition. Spike-V is implemented in Matlab’s Simulink modelling environment.