Speeding up the score computation of HMM speech regognizers with the bucket voronoi intersection algorithm

@inproceedings{Fritsch1995SpeedingUT,
  title={Speeding up the score computation of HMM speech regognizers with the bucket voronoi intersection algorithm},
  author={J{\"u}rgen Fritsch and Ivica Rogina and Tilo Sloboda and Alexander H. Waibel},
  booktitle={EUROSPEECH},
  year={1995}
}
With increasing sizes of speech databases, speech recognizers with huge parameter spaces have become trainable. However, the time and memory requirements for high accuracy re-altime 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… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • 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%.

Citations

Publications citing this paper.
SHOWING 1-10 OF 11 CITATIONS

References

Publications referenced by this paper.