Preprocessing of Dysarthric Speech in Noise Based on CV–Dependent Wiener Filtering

Abstract

In this paper, we propose a consonant–vowel (CV) dependentWiener filter for dysarthric automatic speech recognition (ASR) in noisy environments. When a Wiener filter is applied to dysarthric speech in noise, it distorts initial consonants of dysarthric speech. This is because compared to normal speech, the speech spectrum at a consonant-vowel onset in dysarthric speech is much similar to that of noise, thus speech at the onset is easy to be removed by the Wiener filtering. In order to mitigate this problem, the transfer function of a Wiener filter is differently constructed depending on the result of CV classification that is performed by combining voice activity detection (VAD) and vowel onset estimation. In this work, VAD is done by a statistical model based approach and the vowel onset estimation is by investigating the variation of linear prediction residual signals. To demonstrate the effectiveness of the proposed CV–dependentWiener filter on the performance of dysarthric ASR, we compare the performance of an ASR system employing the proposed method with that using a conventional Wiener filter for different groups of degrees of disability under different signal–to–noise ratio conditions. Consequently, it is shown from the ASR experiments that the proposed Wiener filter achieves a relative average word error rate reduction of 10.41%, 6.03%, and 0.94% for the mild, moderate, and severe group of disability, respectively, when compared to the conventional Wiener filter.