Non-Intrusive Speech Quality Prediction Using Modulation Energies and LSTM-Network
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7682
- Type
- D - Journal article
- DOI
-
10.1109/taslp.2019.2912123
- Title of journal
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Article number
- -
- First page
- 1151
- Volume
- 27
- Issue
- 7
- ISSN
- 2329-9290
- Open access status
- Deposit exception
- Month of publication
- April
- 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
- No
- Number of additional authors
-
5
- Research group(s)
-
G - Speech and Hearing
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first paper that uses neural networks for quality assessment in mis-tuned signal enhancement scenarios that often appear in the real world and thus allows for comparison of different algorithm classes. The paper led to an invitation by the German standardization body VDE to contribute to the extension of current standards for speech quality assessment (Contact: Head of Group "Personalized Hearing Systems" and "Audio Quality and Auditory Modeling" at Fraunhofer IDMT).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -