Supplementary data for "An Investigation into Using Parallel Data for Far-Field Speech Recognition"
Repository URI
Repository DOI
Change log
Authors
Description
Description of the Speech Recognition Training and Test Data and its Availability used for Experiments. Key Speech Recognition Outputs/Detailed Scoring Results used in the paper.
Version
Software / Usage instructions
Speech Recognition outputs are in NIST ctm format (a standard text format used for speech recognition) and .sys files are output of speech recognition scoring process
Keywords
Publisher
University of Cambridge
Rights and licensing
Except where otherwised noted, this item's license is described as Attribution-NonCommercial-NoDerivs 2.0 UK: England & Wales
Sponsorship
This work was supported by the EPSRC [grant number EP/I031022/1], NSF (IIS), DARPA (LORELEI), Google, Microsoft, Amazon, Mitsubishi Electric, and MERL.