Modelling Timbral Hardness
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 33 - Music, Drama, Dance, Performing Arts, Film and Screen Studies
- Output identifier
- 9001533_3
- Type
- D - Journal article
- DOI
-
10.3390/app9030466
- Title of journal
- Applied Sciences
- Article number
- -
- First page
- 466
- Volume
- 9
- Issue
- 3
- ISSN
- 2076-3417
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- 12 - Engineering
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Factual information about significance: Comprehensive accurate metadata is key to user searching of audio and sound effect libraries but can be generated automatically only if suitable extraction tools exist. One of the most common timbral metadata descriptors is 'hardness'. This special-issue paper develops the first source-type-agnostic timbral hardness model. It uses novel acoustic feature extraction, achieves human-equivalent accuracy, and, for the first time, allows automatic hardness annotation of soundfiles. The freely-available python implementation has already been adopted by freesound.org (frederic.font@upf.edu) to allow API searching of its vast online audio database using hardness-based queries, e.g. https://iosr.uk/freesound
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -