We present the development and characteristics of a basic ASR system for isolated digits in Spanish, used over the telephone line. Initially we will introduce our first idea, a basic discrete system, and then we will see the improvements we made to increase the recognition rate at a low CPU cost (always considering its practical implementation as a real time system). The most remarkable advances were obtained with: 1) Semicontinuous modelling. It is a more precise modelling, although more time consuming. 2) End-pointing with a Neural network. 3) One pass decoding with noise models. The intention of both 2 and 3 is to alleviate the effects of a wrong end-pointing. 4) Parametrization using perceptual filters in frequency and filtering in the time domain (RASTA-PLP). We wanted to decrease the effect of telephonic noise in our system.
Cite as: Cordoba, R.d., Menendez-Pidal, X., Macias-Guarasa, J., Gallardo, A., Pardo, J.M. (1995) Development and improvement of a real-time ASR system for isolated digits in Spanish over the telephone line. Proc. 4th European Conference on Speech Communication and Technology (Eurospeech 1995), 1537-1540, doi: 10.21437/Eurospeech.1995-376
@inproceedings{cordoba95_eurospeech,
author={Ricardo de Cordoba and Xavier Menendez-Pidal and Javier Macias-Guarasa and Ascension Gallardo and José M. Pardo},
title={{Development and improvement of a real-time ASR system for isolated digits in Spanish over the telephone line}},
year=1995,
booktitle={Proc. 4th European Conference on Speech Communication and Technology (Eurospeech 1995)},
pages={1537--1540},
doi={10.21437/Eurospeech.1995-376}
}