Authors
Tara N Sainath, Brian Kingsbury, George Saon, Hagen Soltau, Abdel-rahman Mohamed, George Dahl, Bhuvana Ramabhadran
Publication date
2015/4/30
Journal
Neural Networks
Volume
64
Pages
39-48
Publisher
Pergamon
Description
Abstract Convolutional Neural Networks (CNNs) are an alternative type of neural network
that can be used to reduce spectral variations and model spectral correlations which exist in
signals. Since speech signals exhibit both of these properties, we hypothesize that CNNs
are a more effective model for speech compared to Deep Neural Networks (DNNs). In this
paper, we explore applying CNNs to large vocabulary continuous speech recognition
(LVCSR) tasks. First, we determine the appropriate architecture to make CNNs effective ...
that can be used to reduce spectral variations and model spectral correlations which exist in
signals. Since speech signals exhibit both of these properties, we hypothesize that CNNs
are a more effective model for speech compared to Deep Neural Networks (DNNs). In this
paper, we explore applying CNNs to large vocabulary continuous speech recognition
(LVCSR) tasks. First, we determine the appropriate architecture to make CNNs effective ...
Total citations
Scholar articles
TN Sainath, B Kingsbury, G Saon, H Soltau… - Neural Networks, 2015
Dates and citation counts are estimated and are determined automatically by a computer program.