Speech recognition in adverse environments: a probabilistic approach

@inproceedings{Frey2002SpeechRI,
  title={Speech recognition in adverse environments: a probabilistic approach},
  author={Brendan J. Frey and Trausti T. Kristjansson},
  year={2002}
}
In this thesis I advocate a probabilistic view of robust speech recognition. I discuss the classification of distorted features using an optimal classifier, and I show how the generation of noisy speech can be represented as a generative graphical probability model. By doing so, my aim is to build a conceptual framework that provides a unified understanding of robust speech recognition, and to some extent bridges the gap between a purely signal processing viewpoint and the pattern… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 21 CITATIONS

Reconocimiento robusto de voz con datos perdidos o inciertos

José Andrés González López
  • 2013
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Single microphone source separation using high resolution signal reconstruction

  • 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 2004
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Multisensory speech enhancement in noisy environments using bone-conducted and air-conducted microphones

  • 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)
  • 2014
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

CEPSTRUM DOMAIN LAPLACE DENOISING

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Nonlinear Compensation Using the Gauss–Newton Method for Noise-Robust Speech Recognition

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2012
VIEW 1 EXCERPT
CITES BACKGROUND

A variational perspective on noise-robust speech recognition

  • 2011 IEEE Workshop on Automatic Speech Recognition & Understanding
  • 2011
VIEW 1 EXCERPT
CITES METHODS

Approximate Bayesian robust speech processing

  • 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)
  • 2011
VIEW 3 EXCERPTS
CITES METHODS

Automatic phoneme recognition with Segmental Hidden Markov Models

  • 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)
  • 2011

References

Publications referenced by this paper.
SHOWING 1-10 OF 69 REFERENCES

Fundamentals of speech recognition

  • Prentice Hall signal processing series
  • 1993
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Towards non-stationary model-based noise adaptation for large vocabulary speech recognition

  • 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)
  • 2001
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Speech recognition in noisy environments

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Speech recognition in noisy environments: A survey

  • Speech Communication
  • 1995
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A multiresolution approach to blind separation of speech signals in a reverberant environment

  • 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)
  • 2001

Similar Papers

Loading similar papers…