Learning to associate speech-like sensory and motor states during babbling

Background: Development of the feedback loop of speech production starts during the babbling phase of speech acquisition. Within the first year of lifetime toddlers acquire the ability of imitating auditory stimuli, i.e. they acquire the ability of associating speech-like sensory and motor states. Method: Self-organizing maps and one-layer feed-forward networks were used for modeling this learning behavior within a neural model of speech production. The model includes auditory, proprioceptive, tactile, and motor representations for static as well as for dynamic speech-like events, i.e. proto-vocalic and proto-consonantal states. A three-dimensional articulatory speech synthesizer serves as a front-end device for generating high quality sensory signals. Results: Self-organizing maps are useful for modeling auditory-to-somatosensory as well as for auditory-to-motor mappings. The somatosensory-to-motor mapping is modeled successfully using a one-layer feed-forward net. Conclusion: The neural model of speech production introduced here is capable of describing learning during the babbling phase of speech acquisition. The model is now ready for building up the mental syllabary, i.e. for processing sounds, syllables and words of a specific language.