Vowel Recognition in Simulated Neurons

The neural basis of speech recognition and, more generally, sound processing is not well understood. A simple subset of the task of speech recognition, learning to categorise vowel sounds, provides some insights into the more general problems. A simulated neural system that performs this task is described. The system is based on relatively accurate fatiguing leaky integrate and fire neurons, and learns to categorise three categories of vowel sounds. The input to the system is in the form of neural stimulation that relatively accurately reflects the response of biological neurons in the ear to auditory input. The system correctly categorises 91.71% of the vowel sounds using a five-fold test. The system is a sound model of the neuropsychological task of phoneme categorisation, all be it a far from perfect model. As such, it provides an entry into a better understanding of the neuro-psychological mechanisms behind sound processing.