Evolution of a Rapidly Learned Representation for Speech

Newly born infants are able to finely discriminate almost all human speech contrasts and their phonemic category boundaries are initially identical, even for phonemes outside their target language. A connectionist model is described which accounts for this ability. The approach taken has been to develop a model of innately guided learning in which an artificial neural network (ANN) is stored in a "genome" which encodes its architecture and learning rules. The space of possible ANNs is searched with a genetic algorithm for networks that can learn to discriminate human speech sounds. These networks perform equally well having been trained on speech spectra from any human language so far tested (English, Cantonese, Swahili, Farsi, Czech, Hindi, Hungarian, Korean, Polish, Russian, Slovak, Spanish, Ukranian and Urdu). Training the feature detectors requires exposure to just one minute of speech in any of these languages. Categorisation of speech sounds based on the network representations showed the hallmarks of categorical perception, as found in human infants and adults.