Acoustic Modeling Using Deep Belief Networks

Authors:
A. Mohamed;G. E. Dahl;G. Hinton
Affiliations:
Univ. of Toronto, Toronto, ON, Canada;-;-
Venue:
IEEE Transactions on Audio, Speech, and Language Processing
Year:
2012

Citing 0
Cited 7

A better way to learn features: technical perspective

Communications of the ACM
An efficient learning procedure for deep boltzmann machines

Neural Computation
Exploiting deep neural networks for detection-based speech recognition

Neurocomputing
Automatic speech recognition for under-resourced languages: A survey

Speech Communication
Deep feature learning using target priors with applications in ECoG signal decoding for BCI

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Noise-robust speech recognition through auditory feature detection and spike sequence decoding

Neural Computation
An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.02

Visualization

Abstract

Gaussian mixture models are currently the dominant technique for modeling the emission distribution of hidden Markov models for speech recognition. We show that better phone recognition on the TIMIT dataset can be achieved by replacing Gaussian mixture models by deep neural networks that contain many layers of features and a very large number of parameters. These networks are first pre-trained as a multi-layer generative model of a window of spectral feature vectors without making use of any discriminative information. Once the generative pre-training has designed the features, we perform discriminative fine-tuning using backpropagation to adjust the features slightly to make them better at predicting a probability distribution over the states of monophone hidden Markov models.