Feature Compensation with Model-Based Estimation for Noise Masking

Young Joon Kim, Nam Soo KimIEICE Trans. Information and Systems 2007 · OpenReview

Abstract

In this letter, we propose a new approach to estimate the degree of noise masking based on a sophisticated model for clean speech distribution. This measure, named as noise masking probability (NMP), is incorporated into the feature compensation technique to achieve robust speech recognition in noisy environments. Experimental results show that the proposed approach improves the performance of the baseline recognition system in the presence of various background noises.
BibTeX
@article{kim2007feature,
  author = {Young Joon Kim and Nam Soo Kim},
  title = {{Feature Compensation with Model-Based Estimation for Noise Masking}},
  journal = {IEICE Trans. Information and Systems},
  year = {2007},
  url = {https://openreview.net/forum?id=RFWVntDaa9},
}

Loading related content...

Figure