Skip to Main content Skip to Navigation
Conference papers

Speech Enhancement Using AR Model Driven by White Noise with Time-Varying Variance

Abstract : In this paper, the autoregressive (AR) model driven by a white noise with a time-varying variance is proposed for speech signal modeling. An iterative parameter estimation method is then presented, based on the analysis of the short segment (2~4ms) of Linear Prediction (LP) residual. This approach is then used in the framework of speech enhancement based on Kalman filter. A comparative study with existing methods is proposed and shows that the adopted model provides a higher improvement of Signal to Noise Ratio (SNR) than the ordinary AR model.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-00167766
Contributor : Eric Grivel Connect in order to contact the contributor
Submitted on : Wednesday, August 22, 2007 - 4:35:13 PM
Last modification on : Thursday, January 11, 2018 - 6:21:07 AM

Identifiers

  • HAL Id : hal-00167766, version 1

Citation

Hong Cai, Eric Grivel, Mohamed Najim. Speech Enhancement Using AR Model Driven by White Noise with Time-Varying Variance. COST 276, 2002, Budapest, Hungary. pp. ⟨hal-00167766⟩

Share

Metrics

Record views

143