Sehgal, S., Cunningham, S. and Green, P. (2019) Phase-based feature representations for improving recognition of dysarthric speech. In: 2018 IEEE Spoken Language Technology Workshop (SLT). 2018 IEEE Spoken Language Technology Workshop (SLT), 18-21 Dec 2018, Athens, Greece. IEEE , pp. 13-20. ISBN 978-1-5386-4334-1
Abstract
Dysarthria is a neurological speech impairment, which usually results in the loss of motor speech control due to muscular atrophy and incoordination of the articulators. As a result the speech becomes less intelligible and difficult to model by machine learning algorithms due to inconsistencies in the acoustic signal and data sparseness. This paper presents phase-based feature representations for dysarthric speech that are exploited in the group delay spectrum. Such representations are found to be better suited to characterising the resonances of the vocal tract, exhibit better phone discrimination capabilities in dysarthric signals and consequently improve ASR performance. All the experiments were conducted using the UASPEECH corpus and significant ASR gains are reported using phase-based cepstral features in comparison to the standard MFCCs irrespective of the severity of the condition.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2018 IEEE. |
Keywords: | Dysarthric speech recognition; adaptation; group delay spectrum; phase-based cepstrals |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Medicine, Dentistry and Health (Sheffield) > Department of Human Communication Sciences (Sheffield) The University of Sheffield > Faculty of Medicine, Dentistry and Health (Sheffield) > School of Health and Related Research (Sheffield) > ScHARR - Sheffield Centre for Health and Related Research |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 02 Aug 2019 09:39 |
Last Modified: | 02 Aug 2019 09:39 |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/SLT.2018.8639031 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:146836 |