8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


HARTFEX: A Multi-Dimensional System of HMM Based Recognisers for Articulatory Features Extraction

Tarek Abu-Amer, Julie Carson-Berndsen

University College Dublin, Ireland

HARTFEX is a novel system that employs several tiers of HMMs recognisers that work in parallel to extract multi-dimensions of articulatory features. The features segments on the different tiers overlap to account for the co-articulation phenomena. The overlap and precedence relation among features are applied to a phonological parser for further processing. HARTFEX system is built on a modified version of HTK toolkit that allows it to perform multi-thread multi-feature recognition. The system testing results are highly promising. The recognition accuracy for vowel is 98% and for rhotic is 93%. Current work investigates inherited interdependencies of extracting different feature sets.

Full Paper

Bibliographic reference.  Abu-Amer, Tarek / Carson-Berndsen, Julie (2003): "HARTFEX: a multi-dimensional system of HMM based recognisers for articulatory features extraction", In EUROSPEECH-2003, 2541-2544.