Missing-Data Techniques: Feature Reconstruction

@inproceedings{Gemmeke2012MissingDataTF,
  title={Missing-Data Techniques: Feature Reconstruction},
  author={Jort F. Gemmeke and Ulpu Remes},
  booktitle={Techniques for Noise Robustness in Automatic Speech Recognition},
  year={2012}
}
Automatic speech recognition (ASR) performance degrades rapidly when speech is corrupted with increasing levels of noise. Missing data techniques (MDT) constitute a family of methods that tackle noise robust speech recognition based on the so called missing data assumption proposed in [1]. MDTs assume that (i) the noisy speech signal can be divided in speech-dominated (reliable) and noise-dominated (unreliable) spectro-temporal components prior to decoding and (ii) the unreliable elements do… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 51 REFERENCES

Bounded conditional mean imputation with Gaussian mixture models: A reconstruction approach to partly occluded features

  • 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Missing data imputation using compressive sensing techniques for connected digit recognition

  • 2009 16th International Conference on Digital Signal Processing
  • 2009
VIEW 4 EXCERPTS

Reconstructing spectral vectors with uncertain spectrographic masks for robust speech recognition

  • IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.
  • 2005
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Robust speech recognition using missing data techniques in the prospect domain and fuzzy masks

  • 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2008
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Robust speech recognition using cepstral domain missing data techniques and noisy masks

  • 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 2004
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL