Signal subspace approach for psychoacoustically motivated speech enhancement
- 1 February 2011
- journal article
- Published by Elsevier BV in Speech Communication
- Vol. 53 (2), 210-219
- https://doi.org/10.1016/j.specom.2010.09.002
Abstract
In this paper we deal with the perceptually motivated signal subspace methods for speech enhancement. We focus on extended spectral-domain-constrained (SDC) estimator. It is obtained using Lagrange multipliers method. We present an algorithm for a precise computation of the Lagrange multipliers, allowing for a direct shaping the residual noise power spectrum. In addition the SDC estimator is presented in a new, possibly more effective form. As a practical implementation of the estimator we propose perceptually constrained signal subspace (PCSS) method for speech enhancement. The approach utilizes masking phenomena for residual noise shaping and is optimal for the case of coloured noise. Also, less demanding approximate version of this method is derived. Finally comparative evaluation of the most known subspace-based methods is performed using objective speech quality measures and listening tests. Results show that the PCSS method outperforms other methods providing high noise attenuation and better speech quality.Keywords
This publication has 10 references indexed in Scilit:
- Incorporating the human hearing properties in the signal subspace approach for speech enhancementIEEE Transactions on Speech and Audio Processing, 2003
- A generalized subspace approach for enhancing speech corrupted by colored noiseIEEE Transactions on Speech and Audio Processing, 2003
- Extension of the signal subspace speech enhancement approach to colored noiseIEEE Signal Processing Letters, 2003
- An adaptive KLT approach for speech enhancementIEEE Transactions on Speech and Audio Processing, 2001
- Signal/noise KLT based approach for enhancing speech degraded by colored noiseIEEE Transactions on Speech and Audio Processing, 2000
- Single channel speech enhancement using principal component analysis and MDL subspace selectionPublished by International Speech Communication Association ,1999
- A signal subspace approach for speech enhancementIEEE Transactions on Speech and Audio Processing, 1995
- Projection approximation subspace trackingIEEE Transactions on Signal Processing, 1995
- DARPA TIMIT:Published by National Institute of Standards and Technology (NIST) ,1993
- Transform coding of audio signals using perceptual noise criteriaIEEE Journal on Selected Areas in Communications, 1988