IBM / Neural Networks / GPU / Learning Recurrent Neural Networks / Google / Training Recurrent Neural Networks / New York Times / Microsoft / DEEP NEURAL NETWORKS / /
Country
United States / Canada / /
Facility
University of Montreal / University of Toronto / /
IndustryTerm
software engineering / grid search / recent solution / machine learning algorithms / back-propagation algorithm / online learning / unsupervised learning algorithm / distributed deep networks / much faster hardware / parameter server / belief networks / signal processing / discriminative back-propagation algorithm / language processing / convex networks / narrowband telephony speech recognition / semi-online / deep belief networks / systems / recurrent networks / music processing / speech processing / faster hardware / research groups / pre-processing / learning algorithm / voice search / /
MusicAlbum
SPEECH / /
Organization
University of Montreal / University of Toronto / /
Person
G. Hinton / J. Nam / J. Ngiam / H. Lee / M. Devin / P. Nguyen / G. Heigold / V / B. Ramabhadran / A. Khosla / T. N. Sainath / H. Soltau / J. Huang / A. Ng / A. Mohamed / K. Yang / N. Jaitly / B. Kingsbury / J. Dean / P. Novak / P. Fousek / M. Ranzato / P. Tucker / Tony Robinson / V. Vanhoucke / T. Sainath / M. Kim / /
NEW TYPES OF DEEP NEURAL NETWORK LEARNING FOR SPEECH RECOGNITION AND RELATED APPLICATIONS: AN OVERVIEW Li Deng1, Geoffrey Hinton2, and Brian Kingsbury3 1 Microsoft Research, Redmond, WA, USA 2