Introduction to the Special Section on Deep Learning for Speech and Language Processing

Current speech recognition systems, for example, typically use Gaussian mixture models (GMMs), to estimate the observation (or emission) probabilities of hidden Markov models (HMMs), and GMMs are generative models that have only one layer of latent variables. Instead of developing more powerful mode...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on audio, speech, and language processing speech, and language processing, 2012-01, Vol.20 (1), p.4-6
Main Authors: Dong Yu, Hinton, G., Morgan, N., Jen-Tzung Chien, Sagayama, S.
Format: Article
Language:English
Subjects:
Automatic speech recognition
Hidden Markov models
Machine learning
Special issues and sections
Speech recognition
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current speech recognition systems, for example, typically use Gaussian mixture models (GMMs), to estimate the observation (or emission) probabilities of hidden Markov models (HMMs), and GMMs are generative models that have only one layer of latent variables. Instead of developing more powerful models, most of the research effort has gone into finding better ways of estimating the GMM parameters so that error rates are decreased or the margin between different classes is increased. The same observation holds for natural language processing (NLP) in which maximum entropy (MaxEnt) models and conditional random fields (CRFs) have been popular for the last decade. Both of these approaches use shallow models whose success largely depends on the use of carefully handcrafted features.
ISSN:1558-7916
1558-7924
DOI:10.1109/TASL.2011.2173371