Sixth European Conference on Speech Communication and Technology
At ICSLP’98 we presented some preliminary results on automatic preselection list length estimation using parametric and non-parametric techniques, for a flexible large and very large vocabulary, speaker independent, isolated-word hypothesis generation system in a telephone environment, with vocabularies of up to 10000 words. In the baseline system, the preselection module generates a fixed-length list of candidate words, to be given to the verification stage. Our idea is making this length variable, depending on any known-in-advance system parameter, to allow decreasing computational demands. In this paper we present a novel approach to preselection list length estimation. A neural network is used to give an initial estimate of the required length, which is further processed to obtain a final value. The key factor to evaluate different methods is calculating the average preselection list length (effort) while keeping the required error rate.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Macías-Guarasa, J. / Ferreiros, J. / Gallardo, A. / San-Segundo, R. / Pardo, Juan Manuel / Villarrubia, L. (1999): "Variable preselection list length estimation using neural networks in a telephone speech hypothesis-verification system", In EUROSPEECH'99, 295-298.