Noise Compensation using Spectrogram Morphological Filtering
نویسندگان
چکیده
This paper describes the application of morphological filtering to speech spectrograms for noise robust automatic speech recognition. Speech regions of the spectrogram are identified based on the proximity of high energy regions to neighbouring high energy regions in the three-dimensional space. The process of erosion can remove noise while dilation can then restore any erroneously removed speech regions. The combination of the two techniques results in a non-linear, time-frequency filter. Automatic speech recognition experiments are performed on the AURORA database and results show an average relative improvement of 10% is delivered with the morphological filtering approach. When combined with quantile-based noise estimation and non-linear spectral subtraction, the average relative performance improvement is also 10% but with a different performance profile in terms of SNR.
منابع مشابه
Morphological filtering of speech spectrograms in the context of additive noise
A recent approach to signal segmentation in additive noise [1, 2] uses features of small spectrogram sub-units accrued over the full spectrogram. The original work considered chirp signals in additive white Gaussian noise. This paper extends this work first by considering similar signals at different signal-to-noise ratios and then in the context of speech recognition. For the chirp case, a cos...
متن کاملA dynamic system approach to speech enhancement using the H∞ filtering algorithm
This paper presents a new approach to speech enhancement based on the H1 filtering. This approach differs from the traditional modified Wiener/Kalman filtering approach in the following two aspects: 1) no a priori knowledge of the noise source statistics is required, the only assumption made is that noise signals have a finite energy; 2) the estimation criterion for the filter design is to mini...
متن کاملRobust Space/Spatial-Frequency based Filtering of Images in the presence of heavy tailed noise
A robust space/spatial-frequency representation for analysis of two-dimensional signals corrupted by heavy tailed noise is proposed. The L-estimate forms of robust short-time Fourier transform and spectrogram for 2D signals are introduced. They are used to define a non-stationary space-varying filtering procedure in the space/spatial-frequency domain. The efficiency of the proposed procedure is...
متن کاملRobust Speech Recognition: The case for restoring missing features
Speech recognition systems perform poorly in the presence of corrupting noise. Missing feature methods attempt to compensate for the noise by removing unreliable noise corrupted components of a spectrographic representation of the noisy speech and performing recognition with the remaining reliable components. Conventional classifiercompensation methods modify the recognition system to work with...
متن کاملA Divide and Conquer Strategy for Musical Noise-free Speech Enhancement in Adverse Environments
A divide and conquer strategy for enhancement of noisy speeches in adverse environments involving lower levels of SNR is presented in this paper, where the total system of speech enhancement is divided into two separate steps. The first step is based on noise compensation on short time magnitude and the second step is based on phase compensation. The magnitude spectrum is compensated based on a...
متن کامل