Alharbi, S., Simons, A.J.H. orcid.org/0000-0002-5925-7148, Brumfitt, S. et al. (1 more author) (2017) Automatic recognition of children’s read speech for stuttering application. In: 6th. Workshop on Child Computer Interaction (WOCCI 2017), eds. K. Evanini, M. Najafian, S. Safavi and K. Berkling. 6th International Workshop on Child Computer Interaction, 13 Nov 2017, Glasgow, UK. International Speech Communication Association (ISCA) , Glasgow , pp. 1-6.
Abstract
Stuttering is a common speech disfluency that may persist into adulthood if not treated in its early stages. Techniques from spoken language understanding may be applied to provide auto-mated diagnoses of stuttering from voice recordings; however,there are several difficulties, including the lack of training data involving young children and the high dimensionality of these data. This study investigates how automatic speech recognition(ASR) could help clinicians by providing a tool that automatically recognises stuttering events and provides a useful written transcription of what was said. In addition, to enhance the performance of ASR and to alleviate the lack of stuttering data, this study examines the effect of augmenting the language model with artificially generated data. The performance of the ASR tool with and without language model augmentation is com-pared. Following language model augmentation, the ASR tool’s performance improved recall from 38% to 62.2% and precision from 56.58% to 71%. When mis-recognised events are more coarsely classified as stuttering/ non-stuttering events, the performance improves up to 73% in recall and 84% in precision.Although the obtained results are not perfect, they map to fairly robust stutter/ non-stutter decision boundaries.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | @ 2017 International Speech Communication Association. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | speech recognition; human-computer interaction; stuttering recognition; ASR for children |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 16 May 2018 12:33 |
Last Modified: | 16 May 2018 12:33 |
Published Version: | http://dx.doi.org/10.21437/WOCCI.2017-1 |
Status: | Published |
Publisher: | International Speech Communication Association (ISCA) |
Refereed: | Yes |
Identification Number: | 10.21437/WOCCI.2017-1 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:130760 |