Recurrent lateral inhibitory spiking networks for speech enhancement
- Submitting institution
-
University of East London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 31
- Type
- E - Conference contribution
- DOI
-
10.1109/IJCNN.2016.7727310
- Title of conference / published proceedings
- 2016 International Joint Conference on Neural Networks (IJCNN)
- First page
- 1023
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- -
- Year of publication
- 2016
- URL
-
https://ieeexplore.ieee.org/abstract/document/7727310
- 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
- No
- Number of additional authors
-
4
- Research group(s)
-
1 - Intelligent Systems
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper outlines a novel noise removal and speech enhancement technique utilising spiking neural networks. The technique mimics the way humans process speech in noisy environments, and it has been applied to real-world noisy speech recordings. This work is a collaboration with the SME Intelligent Voice Ltd.*, which apply their speech recognition software in banks, prisons and courtrooms, and it led to an Innovate UK funded project with Intelligent Voice, Grant no. 104817, focused on natural language processing for speech.
*Dr Cornelius Glackin, Research Lead, Intelligent Voice Ltd.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -