Imposing dynamic constraints on articulatory representations

A new approach is described which estimates vocal tract shape sequences for speech consisting of voiceless speech and periods of silence as well as voiced speech. The method takes into account differences in the articulatory-acoustic mapping for each of these three difference classes, whilst the same dynamic constraints are applied across all portions of the speech. This method, based on the use of articulatory codebooks, has proved successful in identifying the place position of stops and fricatives.