Data underpinning "I-Vector Estimation Using Informative Priors for Adaptation of Deep Neural Networks"
University of Cambridge
MetadataShow full item record
Karanasou, P., Gales, M., & Woodland, P. (2015). Data underpinning "I-Vector Estimation Using Informative Priors for Adaptation of Deep Neural Networks" [Dataset]. https://www.repository.cam.ac.uk/handle/1810/248387
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.
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 to compute word error rates.
Speech Recognition, Speaker Adaptation, Deep Neural Networks
Publication Reference: http://www.isca-speech.org/archive/interspeech_2015/i15_2872.html
This work was supported by the EPSRC [EPSRC Natural Speech Technology programme grant http://www.natural-speech-technology.org/]
This work was supported by EPSRC [grant number EP/I031022/1].
This record's URL: https://www.repository.cam.ac.uk/handle/1810/248387
Attribution-NonCommercial-NoDerivs 2.0 UK: England & Wales
Licence URL: http://creativecommons.org/licenses/by-nc-nd/2.0/uk/