An uncertainty decoding approach to noise- and reverberation-robust speech recognition

  title={An uncertainty decoding approach to noise- and reverberation-robust speech recognition},
  author={Roland Maas and Akshaya Thippur and Armin Sehr and Walter Kellermann},
  journal={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
The generic REMOS (REverberation MOdeling for robust Speech recognition) concept is extended in this contribution to cope with additional noise components. REMOS originally embeds an explicit reverberation model into a hiddenMarkov model (HMM) leading to a relaxed conditional independence assumption for the observed feature vectors. During recognition, a nonlinear optimization problem is to be solved in order to adapt the HMMs' output probability density functions to the current reverberation… CONTINUE READING


Publications citing this paper.
Showing 1-2 of 2 extracted citations


Publications referenced by this paper.
Showing 1-10 of 25 references

A model-based approach to joint compensation of noise and reverberation for speech recognition

  • A. Krüger, R. Haeb-Umbach
  • Robust speech recognition of uncertain or missing…
  • 2011
1 Excerpt

Similar Papers

Loading similar papers…