Boosting Gaussian mixtures in an LVCSR system

In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale spe...

Full description

Saved in:
Bibliographic Details
Main Authors: Zweig, G., Padmanabhan, M.
Format: Conference Proceeding
Language:English
Subjects:
Acoustic applications
Acoustic testing
Boosting
Error analysis
Large-scale systems
Neural networks
Probability distribution
Speech recognition
System testing
Voice mail
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2000.861945