Skip to main content

A Novel Speech/Noise Discrimination Method for Embedded ASR System

Abstract

The problem of speech/noise discrimination has become increasingly important as the automatic speech recognition (ASR) system is applied in the real world. Robustness and simplicity are two challenges to the speech/noise discrimination method for an embedded system. The energy-based feature is the most suitable and applicable feature for speech/noise discrimination for embedded ASR system because of effectiveness and simplicity. A new method based on a noise model is proposed to discriminate speech signals from noise signals. The noise model is initialized and then updated according to the signal energy. The experiment shows the effectiveness and robustness of the new method in noisy environments.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Bian Wu.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Wu, B., Ren, X., Liu, C. et al. A Novel Speech/Noise Discrimination Method for Embedded ASR System. EURASIP J. Adv. Signal Process. 2004, 951918 (2004). https://doi.org/10.1155/S111086570440225X

Download citation

Keywords and phrases

  • noise robustness
  • speech/noise discrimination
  • automatic speech recognition