9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Application of Weighted Finite-State Transducers to Improve Recognition Accuracy for Dysarthric Speech

Omar Caballero Morales, Stephen Cox

University of East Anglia, UK

Standard speaker adaptation algorithms perform poorly on dysarthric speech because of the limited phonemic repertoire of dysarthric speakers. In a previous paper, we proposed the use of "metamodels" to correct dysarthric speech. Here, we report on an improved technique that makes use of a cascade of Weighted Finite-State Transducers (WFSTs) at the confusion-matrix, word and language levels. This approach outperforms both standard MLLR and metamodels.

Full Paper

Bibliographic reference.  Morales, Omar Caballero / Cox, Stephen (2008): "Application of weighted finite-state transducers to improve recognition accuracy for dysarthric speech", In INTERSPEECH-2008, 1761-1764.