Heterogeneous measurements and multiple classifiers for speech recognition

@inproceedings{Halberstadt1998HeterogeneousMA,
  title={Heterogeneous measurements and multiple classifiers for speech recognition},
  author={Andrew K. Halberstadt and James R. Glass},
  booktitle={ICSLP},
  year={1998}
}
This paper addresses the problem of acoustic phonetic modeling. First, heterogeneous acoustic measurements are chosen in order to maximize the acoustic-phonetic information extracted from the speech signal in preprocessing. Second, classifier systems are presented for successfully utilizing high-dimensional acoustic measurement spaces. The techniques used for achieving these two goals can be broadly categorized as hierarchical, committeebased, or a hybrid of these two. This paper presents… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 103 CITATIONS, ESTIMATED 99% COVERAGE

A wavelet and filter bank framework for phonetic classification

  • Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
  • 2005
VIEW 6 EXCERPTS
CITES RESULTS & METHODS
HIGHLY INFLUENCED

Localized spectro-temporal cepstral analysis of speech

  • 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2008
VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

An Implementation of Rational Wavelets and Filter Design for Phonetic Classification

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2007
VIEW 4 EXCERPTS
CITES RESULTS & BACKGROUND
HIGHLY INFLUENCED

A probabilistic framework for segment-based speech recognition

  • Computer Speech & Language
  • 2003
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

TIMIT Acoustic-Phonetic Continuous Speech Corpus

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

1998
2017

CITATION STATISTICS

  • 17 Highly Influenced Citations

  • Averaged 2 Citations per year over the last 3 years

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…