Spectral Estimation of Speech Corrupted by Colored Noise

Noise Whitening - Based Pitch Detection for Speech Highly Corrupted by Colored Noise

The importance of a reliable and accurate pitch detection algorithm is well recognized in the speech processing area because such an algorithm can provide the more accurate spectral and prosody information needed in all speech research fields, such as speech synthesis, voice color conversion, speech coding, and speech recognition [1], [2]. To estimate pitch frequency, a simple average magnitude...

A generalized subspace approach for enhancing speech corrupted by colored noise

A generalized subspace approach is proposed for enhancement of speech corrupted by colored noise. A nonunitary transform, based on the simultaneous diagonalization of the clean speech and noise covariance matrices, is used to project the noisy signal onto a signal-plus-noise subspace and a noise subspace. The clean signal is estimated by nulling the signal components in the noise subspace and r...

Perceptually-constrained generalized singular value decomposition-based approach for enhancing speech corrupted by colored noise

In a previous work, we have successfully integrated the transformation-based signal subspace technique with the generalized singular value decomposition (GSVD) algorithm to develop an improved speech enhancement framework [1]. In this paper, we further incorporate the perceptual masking effect of the psychoacoustics model as extra constraints of the previously proposed GSVD-based algorithm to o...

Estimation of formants in noise corrupted speech using auditory models

Spectral Estimation for Noise Robust Speech Recognition

We present results on the recognition accuracy of a continuous speech, speaker independent HMM recognition system that incorporates a novel noise reduction algorithm. The algorithm is a minimum mean square error estimation tailored for a filter-bank front-end. It introduces a significant improvement over similar published algorithms by incorporating a better statistical model for the filter-ban...