EUROSPEECH '95

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 speakerindependent 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 JANUS2 speech recognizer, which reduces the time for the computation of HMM emission probabilities with large Gaussian mixtures by 50% to 80%.
Bibliographic reference. Fritsch, J. / Rogina, I. / Sloboda, Tilo / Waibel, Alex (1995): "Speeding up the score computation of HMM speech regognizers with the bucket voronoi intersection algorithm", In EUROSPEECH1995, 10911094.