In this paper we present a speech recognition system based on articulatory dynamics. We do not extend the acoustic feature with any explicit articulatory measurements but instead the ar- ticulatory dynamics of speech are structurally embodied within episodic memories. The proposed recognizer is made of differ- ent memories each specialized for a particular articulator. As all the articulators do not contribute equally to the realization of a particular phoneme, the specialized memories do not per- form equally regarding each phoneme. We show, through phone string recognition experiments that combining the recognition hypotheses resulting from the different articulatory specialized memories leads to significant recognition improvements.