DMCA
On Supervised Learning From Sequential Data With Applications For Speech Recognition (1999)
| Citations: | 18 - 1 self |
BibTeX
@MISC{Schuster99onsupervised,
author = {Michael Schuster},
title = {On Supervised Learning From Sequential Data With Applications For Speech Recognition},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
visualization of the problem to model human speech. A large number of example sequences of observation vectors (shown connected as continuous trajectories) depending on a given sequence of class labels, with each class representing for example a phoneme (here the name Keiko with given durations). In this synthetic example, the one-dimensional target data would be represented poorly by a uni-modal Gaussian distribution with a constant variance (which corresponds to using the squared-error objective function), which would average the two separate branches, indicated by the fat lines as the mean and constant variance of the single Gaussian. Compare this figure with Figure 3.10, Figure 3.11 and Figure 3.12 to see a subsequent improvement of the model.
Keyphrases
speech recognition sequential data constant variance name keiko observation vector synthetic example continuous trajectory class label human speech one-dimensional target data example sequence separate branch fat line single gaussian squared-error objective function large number uni-modal gaussian distribution subsequent improvement
