β-Masking MMSE speech enhancement for speech recognition

Abstract

Speech recognition performance deteriorates drastically when they are deployed in practical situation where the speech is corrupted by additive noise. One way to improve the robustness of the speech recognition system is to enhance the speech prior to its recognition. This paper focuses on developing a masking-based ß-order minimum mean square error… (More)

2 Figures and Tables

Topics

  • Presentations referencing similar topics