Robust Binaural Localization of a Target Sound Source by Combining Spectral Source Models and Deep Neural Networks
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2603
- Type
- D - Journal article
- DOI
-
10.1109/TASLP.2018.2855960
- Title of journal
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Article number
- -
- First page
- 2122
- Volume
- 26
- Issue
- 11
- ISSN
- 2329-9290
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2018
- 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
- 19
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Sound source localization using two microphones is a challenging problem with applications in humanoid robotics. The work was funded by the EU project TwoEars (ICT-618075) and led to an ongoing collaboration and further publications with Prof Jens. Blauert, Ruhr University Bochum (doi.org/10.1007/978-3-030-00386-9_1). Additional uptake in Italy, at the Universita Politecnica delle Marche, Ancona, Italy, led to an ERASMUS+ traineeship hosted at Sheffield, and a joint publication at the IEEE ICASSP conference (doi.org/10.1109/ICASSP.2019.8683732).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -