Acoustic Front-End Optimization for Large Vocabulary Speech Recognition (0)
by
L. Welling
,
N. Haberland
,
H. Ney
| Venue: | Proc. EUROSPEECH |
| Citations: | 10 - 7 self |
BibTeX
@INPROCEEDINGS{Welling_acousticfront-end,
author = {L. Welling and N. Haberland and H. Ney},
title = {Acoustic Front-End Optimization for Large Vocabulary Speech Recognition},
booktitle = {Proc. EUROSPEECH},
year = {},
pages = {2099--2102}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper we describe experiments with the acoustic front--end of our large vocabulary speech recognition system. In particular, two aspects are studied: 1) linear transforms for feature extraction and 2) the modelling of the emission probabilities. Experiments are reported on a 5000--word task of the ARPA Wall Street Journal database.
