September
1995
Speeding Up the Score Computation of HMM Speech Recognizers with the Bucket Voronoi Intersection Algorithm
Authors:
Abstract:
With increasing sizes of speech databases, speech recognizers with huge parameter spaces have become trainable. However, the time and memory requirements for high accuracy realtime speaker-independent continuous speech recognition will probably not be met by the available hardware for a reasonable price for the next few years. This paper describes the application of the Bucket Voronoi Intersection algorithm to the JANUS-2 speech recognizer, which reduces the time for the computation of HMM emission probabilities with large Gaussian mixtures by 50% to 80%.
copied = false, 2000);
">
@conference{Fritsch-1995-16158,
author = {Juergen Fritsch And Ivica Rogina And Tilo Sloboda And Alex Waibel},
title = {Speeding Up the Score Computation of HMM Speech Recognizers with the Bucket Voronoi Intersection Algorithm},
booktitle = {Proceedings of 4th European Conference on Speech Communication and Technology (EUROSPEECH '95)},
year = {1995},
month = {September},
volume = {2},
pages = {1091 - 1094},
}
author = {Juergen Fritsch And Ivica Rogina And Tilo Sloboda And Alex Waibel},
title = {Speeding Up the Score Computation of HMM Speech Recognizers with the Bucket Voronoi Intersection Algorithm},
booktitle = {Proceedings of 4th European Conference on Speech Communication and Technology (EUROSPEECH '95)},
year = {1995},
month = {September},
volume = {2},
pages = {1091 - 1094},
}