A probabilistic framework for segment-based speech recognition

@article{Glass2003APF,
  title={A probabilistic framework for segment-based speech recognition},
  author={James R. Glass},
  journal={Computer Speech & Language},
  year={2003},
  volume={17},
  pages={137-152}
}
Most current speech recognizers use an observation space based on a temporal sequence of measurements extracted from fixed-length ‘‘frames’’ (e.g., Mel-cepstra). Given a hypothetical word or sub-word sequence, the acoustic likelihood computation always involves all observation frames, though the mapping between individual frames and internal recognizer states will depend on the hypothesized segmentation. There is another type of recognizer whose observation space is better represented as a… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 268 CITATIONS, ESTIMATED 24% COVERAGE

Metadiscourse tagging in academic lectures

VIEW 6 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Language Modeling for limited-data domains

VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

One-Pass Coarse-to-Fine Segmental Speech Decoding Algorithm

  • 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings
  • 2006
VIEW 12 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

On the Use of Acoustic Unit Discovery for Language Recognition

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2016
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2003
2019

CITATION STATISTICS

  • 43 Highly Influenced Citations

  • Averaged 7 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Acoustic modelling improvements in a segmentbased speech recognizer

N. om, L. Hetherington, T. Hazen, E. Sandness, J. Glass
  • Proc. IEEE Automatic Speech Recognition and Understanding Workshop,
  • 1999

Similar Papers

Loading similar papers…