Single-channel speech enhancement based on joint constrained dictionary learning

Abstract

To improve the performance of speech enhancement in a complex noise environment, a joint constrained dictionary learning method for single-channel speech enhancement is proposed, which solves the “cross projection” problem of signals in the joint dictionary. In the method, the new optimization function not only constrains the sparse representation of the noisy signal in the joint dictionary, and controls the projection error of the speech signal and noise signal on the corresponding sub-dictionary, but also minimizes the cross projection error and the correlation between the sub-dictionaries. In addition, the adjustment factors are introduced to balance the weight of constraint terms to obtain the joint dictionary more discriminatively. When the method is applied to the single-channel speech enhancement, speech components of the noisy signal can be more projected onto the clean speech sub-dictionary of the joint dictionary without being affected by the noise sub-dictionary, which makes the quality and intelligibility of the enhanced speech higher. The experimental results verify that our algorithm has better performance than the speech enhancement algorithm based on discriminative dictionary learning under white noise and colored noise environments in time domain waveform, spectrogram, global signal-to-noise ratio, subjective evaluation of speech quality, and logarithmic spectrum distance.

An MMSE graph spectral magnitude estimator for speech signals residing on an undirected multiple graph

“…In this Appendix, we derive the gain function (28) of MMSE graph magnitude estimator, the denominator fraction ζ in (22)…”

“…In addition, in [27], the authors proposed a statistical speech enhancement model using acoustic environment classification supported by a Gaussian mixture model. In [28], the authors proposed a joint-constrained dictionary learning method to solve the "cross projection" problem of signals in the joint dictionary for single-channel speech enhancement.…”

Multi-channel dictionary learning speech enhancement based on power spectrum

“…The above classical algorithm performs well in stationary noise, but is weak in dealing with non-stationary noise [7]. Speech enhancement algorithm using speech and noise prior information; Including hidden Markov model method [8], non-negative matrix decomposition [9][10], dictionary learning [11][12][13], etc., the effect of dealing with non-stationary noise is obviously better than that of classical methods without prior knowledge [14].…”