Deep learning-based automated speech detection as a marker of social functioning in late-life depression
- Submitting institution
-
University of Northumbria at Newcastle
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 27499614
- Type
- D - Journal article
- DOI
-
10.1017/S0033291719003994
- Title of journal
- Psychological Medicine
- Article number
- -
- First page
- 1
- Volume
- 0
- Issue
- -
- ISSN
- 0033-2917
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
12
- Research group(s)
-
A - Digital Health and Wellbeing (DH&W)
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a deep learning model to automatically detect the total speech and the proportion of speech produced by the device wearer as an indicator for social functioning for late life Depression whilst maintaining the naturalistic setting environment and participants' privacy. This work deals with the challenge of indoor audible speech within background in addition to outdoor noises. This research was supported by the Medical Research Council (grant number G1001828/1), the EPSRC (grant number EP/G066019/1), and Northumberland, Tyne and Wear NHS Foundation Trust Research Capability Funding. The work has an open source code available on Github.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -