Evaluation and Integration of Neural-Network Training Techniques for Continuous Digit Recognition

This paper describes a set of experiments on neural-network
training and search techniques that, when combined, have
resulted in a 54% reduction in error on the continuous digits
recognition task. The best system had word-level accuracy of
97.52% on a test set of the OGI 30K Numbers corpus, which
contains
naturally-produced continuous digit strings recorded
over telephone channels. Experiments investigated effects of
the feature
set, the amount of data used for training, the type of
context-dependent categories to be recognized, the values for
duration limits, and the type of grammar. The experiments
indicate that the grammar and duration limits had a greater
effect on recognition accuracy than the output categories,
cepstral features, or a 50% increase in the amount of training
data.

Publication type: 
Contributo in atti di convegno
Author or Creator: 
Hosom J.P.
Cole R.A.
Cosi P.
Publisher: 
Causal Production Pty Ltd, Rundle Mall (PO Box 100), AUS
Source: 
ICSLP-98, International Conference on Spoken Language Processing, pp. 732–734, Sydney, Australia, 30 Nov. - 4 December, 1998
Date: 
1998
Resource Identifier: 
http://www.cnr.it/prodotto/i/241073
http://www.pd.istc.cnr.it/Papers/PieroCosi/cp-ICSLP98-1.pdf
Language: 
Eng
ISTC Author: 
Piero Cosi's picture
Real name: