George Saon

Speaker adaptation of neural network acoustic models using i-vectors

George Saon, Hagen Soltau, D. Nahamoo et al. · 2013 · 606 citations

Computing, Communication, Acoustics +11

Deep Convolutional Neural Networks for Large-scale Speech Tasks

Tara N. Sainath, Brian Kingsbury, George Saon et al. · Neural Networks · 2014 · 501 citations

Computing, Computer Science, Feature Engineering +13

Boosted MMI for model and feature-space discriminative training

Daniel Povey, Dimitri Kanevsky, Brian Kingsbury et al. · Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing · 2008 · 347 citations

Computing, Computer Science, Machine Learning +11

fMPE: Discriminatively Trained Features for Speech Recognition

Daniel Povey, Brian Kingsbury, Lidia Mangu et al. · 2006 · 278 citations

Computing, Computer Science, Feature Engineering +6

Maximum likelihood discriminant feature spaces

George Saon, M. Padmanabhan, R. Gopinath et al. · 2002 · 196 citations

Computing, Computer Science, Discrimination +16