A data-driven approach to optimizing spectral speech enhancement methods for various error criteria

Gain functions for spectral noise suppression have been derived in literature for some error criteria and statistical models. These gain functions are only optimal when the statistical model is correct and the speech and noise spectral variances are known. Unfortunately, the speech distributions are unknown and can at best be determined conditionally on the estimated spectral variance. We show that the “decision-directed” approach for speech spectral variance estimation can have an important bias at low SNRs, which generally leads to too much speech suppression. To correct for such estimation inaccuracies and adapt to the unknown speech statistics, we propose a general optimization procedure, with two gain functions applied in parallel. A conventional algorithm is run in the background and is used for a priori SNR estimation only. For the final reconstruction a different gain function is used, optimized for a wide range of signal-to-noise ratios. The gain function providing for the reconstruction is trained on a speech database, by minimizing a relevant error criterion. The procedure is illustrated for several error criteria. The method compares favorably to current state-of-the-art methods, and needs less smoothing in the decision-directed spectral variance estimator.