Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech

Jan Nouza, Petr Cerva, Jan Silovský. Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, May 26-31, 2013. pages 8046-8050, IEEE, 2013. [doi]

Authors

Jan Nouza

This author has not been identified. Look up 'Jan Nouza' in Google

Petr Cerva

This author has not been identified. Look up 'Petr Cerva' in Google

Jan Silovský

This author has not been identified. Look up 'Jan Silovský' in Google