ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Application of weighted finite-state transducers to improve recognition accuracy for dysarthric speech

Omar Caballero Morales, Stephen Cox

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.


doi: 10.21437/Interspeech.2008-485

Cite as: Morales, O.C., Cox, S. (2008) Application of weighted finite-state transducers to improve recognition accuracy for dysarthric speech. Proc. Interspeech 2008, 1761-1764, doi: 10.21437/Interspeech.2008-485

@inproceedings{morales08_interspeech,
  author={Omar Caballero Morales and Stephen Cox},
  title={{Application of weighted finite-state transducers to improve recognition accuracy for dysarthric speech}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={1761--1764},
  doi={10.21437/Interspeech.2008-485}
}