Enhancing Acoustic-to-EPG Mapping with Lip Position Information

This paper investigates the hypothesis that cues involving the positioning of the lips may improve upon a system that per-forms a mapping from acoustic parameters to electropalato-graphic (EPG) information; that is, patterns of contact be-tween the tongue and the hard palate. We adopt a multilayer perceptron as a relatively simple model for the acoustic-to-electropalatographic mapping and demonstrate that its perfor-mance is improved when parameters describing the positioning of the lips recorded by means of electromagnetic articulography (EMA) are added to the input of the model. Index Terms: speech production, inversion, EPG, EMA 1