ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Noise robust recognition using feature selective modeling

Michael K. Brendborg, Borge Lindberg

In automatic speech recognition (ASR) systems immunity to additive noise may either be applied at the preprocessing stage or at the pattern matching stage. The Feature Selective Modeling (FSM) approach suggested in this paper is applied in the pattern matching stage, but in contrast to most existing methods, it is optimized on a model basis such that noise robust and phonetically descriptive parameters of a particular model can be set in focus. For sonorant sounds this is done by marking the lowest n mean values of each HMM density function as being sensitive to noise in a log filterbank representation. The noise robustness is obtained by deemphasizing the marked feature dimensions. Two different methods for de-emphasizing - mean value masking and dimensional reduction - are presented and experimentally compared to the PMC-algorithm [2].


doi: 10.21437/Eurospeech.1997-101

Cite as: Brendborg, M.K., Lindberg, B. (1997) Noise robust recognition using feature selective modeling. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 295-298, doi: 10.21437/Eurospeech.1997-101

@inproceedings{brendborg97_eurospeech,
  author={Michael K. Brendborg and Borge Lindberg},
  title={{Noise robust recognition using feature selective modeling}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={295--298},
  doi={10.21437/Eurospeech.1997-101},
  issn={1018-4074}
}