Cognitively inspired feature extraction and speech recognition for automated hearing loss testing
- Submitting institution
-
University of Wolverhampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1227
- Type
- D - Journal article
- DOI
-
10.1007/s12559-018-9607-4
- Title of journal
- Cognitive Computation
- Article number
- 4
- First page
- 489
- Volume
- 11
- Issue
- 4
- ISSN
- 1866-9956
- Open access status
- Technical exception
- Month of publication
- February
- Year of publication
- 2019
- 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
-
4
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The proposed automated hearing loss testing approach is the first effort to automate pure tone and speech audiometry, identifying both conductive and sensorineural hearing losses at early stages. The proposed method is inspired by the principle of spectrum sensing in cognitive radio and follows the idea of learning and adaptation. This framework is novel with a timely application to a cost-effective, quick, and easy-to-use pre-screening test for predicting hearing loss at an early stage, addressing limitations such as appointment-delays, practitioner-fee, and unavailability of equipment/qualified practitioner, especially in developing countries.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -