Learning to Speak : Speech Production and Sensori

This chapter describes how an artiicial device, able to produce acoustic signals from articulatory motion, can learn to speak, i.e. coordinate its articulatory movements in such a way that it utters meaningful sequences of sounds belonging to a given language. This complex learning procedure, accomplished within a few years by the human child, is simulated in four major steps: (a) a babbling phase, where the device builds up a model of the forward kinematics, i.e. the articulatory-to-audiovisual mapping; (b) an imitation stage, where it tries to reproduce a limited set of sound sequences by audiovisual to -articulatory inversion including a normalization procedure; (c) a shapingg stage, where phonemes are associated with sensori-motor representation; and nally, (d) a rhythmicc phase, where it learns the appropriate coordination of the activations of these sensori-motor targets. This artiicial device has thus an ear which delivers both the control signals and the identiication of percepts. Results of simulations reported in this chapter show that this theoretical framework is supported by quantitative results.