A neural net for processing of stationary signals in the auditory system

In the auditory domain, since the first work by Rose and colleagues, it is well-known that responses in single auditory nerve fibers are phase-locked to the frequency components of an acoustic stimulation. The present authors describe a neural net which intimately links geographical and temporal aspects of neural coding. It is built from: a mathematical property concerning crossed correlations between channels, still true when their content is made of sequences of spikes; and architecture characteristics of real biological neural nets. They apply this model on simplified data, but compatible with those observed by Delgutte (1984) in the auditory nerve. They describe a model of vowel spectrum processing by a tonic channel. This model would be higher than the cochlea and the auditory nerve in the auditory chain, with its input consisting in temporarily organized sequences of spikes