Supplementary data for "Improved DNN-based Segmentation for Multi-genre Broadcast Audio"
Repository URI
Repository DOI
Change log
Authors
Wang, L.
Zhang, C.
Gales, M. J. F.
Karanasou, P.
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
Speech Recognition, Deep Neural Networks, Speech Segmentation
Publisher
University of Cambridge
Sponsorship
This work was supported by the EPSRC [grant number EP/I031022/1] and by Cambridge Commonwealth, European & International Trust.