Authors
Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, Brian Kingsbury
Publication date
2012/11
Journal
IEEE Signal Processing Magazine
Volume
29
Issue
6
Pages
82-97
Publisher
IEEE
Description
Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a
frame or a short window of frames of coefficients that represents the acoustic input. An
alternative way to evaluate the fit is to use a feed-forward neural network that takes several
frames of coefficients as input and produces posterior probabilities over HMM states as
output. Deep neural networks (DNNs) that have many hidden layers and are trained using
new methods have been shown to outperform GMMs on a variety of speech recognition ...
frame or a short window of frames of coefficients that represents the acoustic input. An
alternative way to evaluate the fit is to use a feed-forward neural network that takes several
frames of coefficients as input and produces posterior probabilities over HMM states as
output. Deep neural networks (DNNs) that have many hidden layers and are trained using
new methods have been shown to outperform GMMs on a variety of speech recognition ...
Scholar articles
G Hinton, L Deng, D Yu, GE Dahl, A Mohamed, N Jaitly… - IEEE Signal Processing Magazine, 2012
Dates and citation counts are estimated and are determined automatically by a computer program.