Signal Adaptive Spectral Envelope Estimation for Robust Speech Recognition

Matthias Wölfel

This paper describes a novel spectral envelope estimation technique which adapts to the characteristics of the observed signal. This is possible via the introduction of a second bilinear transformation into warped (MVDR) spectral envelope estimation. As opposed to the first bilinear transformation, however, which is applied in the time domain, the second bilinear transformation must be applied in the frequency domain. This extension enables the resolution of the spectral envelope estimate to be steered to lower or higher frequencies, while keeping the overall resolution of the estimate and the frequency axis fixed. When embedded in the feature extraction process of an automatic speech recognition system, it provides for the emphasis of the characteristics of speech features that are relevant for robust classification, while simultaneously suppressing characteristics that are irrelevant for classification. The change in resolution may be steered, for each observation window, by the normalized first autocorrelation coefficient.

Mots clés: Adaptive Feature Extraction; Spectral Estimation; Minimum Variance Distortionless Response; Automatic Speech Recognition; Bilinear Transformation; Time vs. Frequency Domain

Matthias Wölfel. Signal Adaptive Spectral Envelope Estimation for Robust Speech Recognition. Speech Communication, 2009, 51 (6), pp.551. ⟨10.1016/j.specom.2009.02.006⟩. ⟨hal-00524122⟩