Speeding Up the Score Computation of HMM Speech Recognizers with the Bucket Voronoi Intersection Algorithm
Conference Paper, Proceedings of 4th European Conference on Speech Communication and Technology (EUROSPEECH '95), Vol. 2, pp. 1091 - 1094, September, 1995
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%.
BibTeX
@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},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.