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

Caballero Morales, Omar and Cox, Stephen (2008) Application of Weighted Finite-State Transducers to Improve Recognition Accuracy for Dysarthric Speech. In: 9th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2008-09-22 - 2008-09-26.

Full text not available from this repository. (Request a copy)

Abstract

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.

Item Type: Conference or Workshop Item (Paper)
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Interactive Graphics and Audio
Faculty of Science > Research Groups > Smart Emerging Technologies
Depositing User: Nicola Talbot
Date Deposited: 14 Mar 2011 08:57
Last Modified: 22 Apr 2023 02:44
URI: https://ueaeprints.uea.ac.uk/id/eprint/26020
DOI:

Actions (login required)

View Item View Item