A formal structural representation of speech consistent with the principles of combinatorial structure theory is presented in this paper. The representation is developed within the Evolving Transformation System (ETS) formalism and encapsulates speech processes at the articulatory level. We show how the class structure of several consonantal phonemes of English can be expressed with the help of articulatory gestures-the atomic combinatorial units of speech. As a preliminary step towards the design of a speech recognition architecture based on the structural approaches to physiology and articulatory phonology, we present an algorithm for the structural detection of phonemic class elements inside gestural ETS structures derived from continuous speech. Experiments designed to verify the adequacy of the hypothesised gestural class structure conducted on the MOCHA articulatory corpus are then described. Our experimental results support the hypothesis that the articulatory representation captures sufficient information for the accurate structural identification of the phonemic classes in question.