Exploiting Deep Neural Networks and Head Movements for Robust Binaural Localization of Multiple Sources in Reverberant Environments
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2491
- Type
- D - Journal article
- DOI
-
10.1109/TASLP.2017.2750760
- Title of journal
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Article number
- -
- First page
- 2444
- Volume
- 25
- Issue
- 12
- ISSN
- 1558-7916
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2017
- 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)
-
G - Speech and Hearing
- Citation count
- 40
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first to combine a deep neural network approach to binaural sound localisation with a system for exploiting head movements. Conference papers leading up to this journal publication have been highly cited (total 96 citations from Interspeech2015 and ICASSP2015). Funded by the EU (ICT-618075) and demonstrated at a public event (La Nuit Européenne des Chercheures, Toulouse, 30th September 2016) as part of a robotic hearing system. The system described in the paper has been used as a standard baseline in subsequent research at Peking University (doi.org/10.1049/joe.2019.1207) and Beijing Institute of Technology (doi.org/10.1109/ICSIDP47821.2019.9172979).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -