Errors-In-Variables based identification of autoregressive parameters for speech enhancement using one microphone

Abstract : Parametric approaches based on a priori models of the speech are often used in the framework of speech enhancement using a single microphone. When the speech is modeled by means of a stationary autoregressive (AR) process, a frameby- frame approach is usually considered. However, it requires the unbiased estimations of the autoregressive parameters and of the noise variances for the subsequent implementation of a filter (Kalman, Hinf, etc.). The purpose of this paper is twofold. Firstly, we propose to view the AR parameter estimation as an errors-in-variables issue. Secondly, we implement an optimal smoothing procedure based on a constrained minimum variance estimation of the signal. Then, we test the procedure based on both steps in the field of speech enhancement.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00167721
Contributor : Eric Grivel <>
Submitted on : Wednesday, August 22, 2007 - 2:35:50 PM
Last modification on : Thursday, January 11, 2018 - 6:21:07 AM

Identifiers

  • HAL Id : hal-00167721, version 1

Citation

William Bobillet, Eric Grivel, Mohamed Najim, Roberto Diversi, Roberto Guidorzi, et al.. Errors-In-Variables based identification of autoregressive parameters for speech enhancement using one microphone. ISCCSP (International Symposium on Communications, Control and Signal Processing), 2006, Marrakech, Morocco. pp. ⟨hal-00167721⟩

Share

Metrics

Record views

254