Masked Conditional Neural Networks for sound classification
- Submitting institution
-
University of York
- Unit of assessment
- 12 - Engineering
- Output identifier
- 66412928
- Type
- D - Journal article
- DOI
-
10.1016/j.asoc.2020.106073
- Title of journal
- APPLIED SOFT COMPUTING
- Article number
- 106073
- First page
- -
- Volume
- 90
- Issue
- -
- ISSN
- 1568-4946
- 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
- No
- Number of additional authors
-
2
- Research group(s)
-
A - Communication Technologies
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Using standard performance metrics on widely used benchmark data MCLNN outperforms state-of-the-art alternatives having far more complicated architectures. Code is publicly released on Github (https://github.com/fadymedhat/MCLNN) which reports 150 views/month and six forked versions indicating good industry uptake including by significant industry players. Four masters theses (from four different countries) give early indications of the research being built upon more substantially.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -