Reduction of acoustic model training time and required data passes via stochastic approaches to maximum likelihood and discriminative training

Petr Novák, Roman Otec, Antonio Lee, Vaibhava Goel. Reduction of acoustic model training time and required data passes via stochastic approaches to maximum likelihood and discriminative training. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014. pages 5577-5581, IEEE, 2014. [doi]

Authors

Petr Novák

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

Roman Otec

This author has not been identified. Look up 'Roman Otec' in Google

Antonio Lee

This author has not been identified. Look up 'Antonio Lee' in Google

Vaibhava Goel

This author has not been identified. Look up 'Vaibhava Goel' in Google