Convolutional Neural Networks for Distant Speech Recognition
- Submitting institution
-
University of Edinburgh
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 57884692
- Type
- D - Journal article
- DOI
-
10.1109/LSP.2014.2325781
- Title of journal
- IEEE Signal Processing Letters
- Article number
- -
- First page
- 1120
- Volume
- 21
- Issue
- 9
- ISSN
- 1070-9908
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2014
- 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)
-
D - Language, Interaction and Robotics
- Citation count
- 114
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work pioneered the use of convolutional networks for multi-microphone distant speech recognition and has been widely used by other researchers as a reference baseline for distant speech recognition (e.g. at the Jelinek Workshop in 2016). The approach underpins the distant speech recognition capability of the Emotech Olly robot (contact: CEO) which won four awards at CES-2017. It has formed the basis of an industry project funded by Toshiba Research Europe (2017-2021; £140k) and our EPSRC project SpeechWave (£667k; 2018-2021). IEEE Signal Processing Letters had an accept rate of about 20% in 2014.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -