Speech Enhancement Algorithm Based on Super-Gaussian Modeling and Orthogonal Polynomials

Abstract

Different types of noise from the surrounding always interfere with speech and produce annoying signals for the human auditory system. To exchange speech information in a noisy environment, speech quality and intelligibility must be maintained, which is a challenging task. In most speech enhancement algorithms, the speech signal is characterized by Gaussian or super-Gaussian models, and noise is characterized by a Gaussian prior. However, these assumptions do not always hold in real-life situations, thereby negatively affecting the estimation, and eventually, the performance of the enhancement algorithm. Accordingly, this paper focuses on deriving an optimum low-distortion estimator with models that fit well with speech and noise data signals. This estimator provides minimum levels of speech distortion and residual noise with additional improvements in speech perceptual aspects via four key steps. First, a recent transform based on an orthogonal polynomial is used to transform the observation signal into a transform domain. Second, the noise classification based on feature extraction is adopted to find accurate and mutable models for noise signals. Third, two stages of nonlinear and linear estimators based on the minimum mean square error (MMSE) and new models for speech and noise are derived to estimate a clean speech signal. Finally, the estimated speech signal in the time domain is determined by considering the inverse of the orthogonal transform. The results show that the average classification accuracy of the proposed approach is 99.43%. In addition, the proposed algorithm significantly outperforms existing speech estimators in terms of quality and intelligibility measures.

Real-Time Speech Enhancement Algorithm Based on Attention LSTM

“…Some scholars have adopted super-Gaussian functions to model speech signals because super-Gaussian priors allow for better reduction of noise between speech spectral harmonics than Gaussian estimators such as the Wiener filter [6]. Mahmmod et al propose an optimum low-distortion estimator with models that fit well with speech and noise signals to decrease the deviation of Gaussian or super-Gaussian models [7]. These algorithms are designed based on the complex statistical characteristics of the interaction between noise and clean speech, but they usually assume that the noise signal is relatively stable or changes slowly.…”

On Learning Spectral Masking for Single Channel Speech Enhancement Using Feedforward and Recurrent Neural Networks

“…A number of learning approaches have recently been proposed for estimating spectral-masks with confirmed notable results [17][18][19][20]. Few of the recent related work regarding supervised speech enhancement is available in [21][22][23].…”

Improved Relativistic Cycle-Consistent GAN With Dilated Residual Network and Multi-Attention for Speech Enhancement

“…Past speech enhancement methods fall into two categories: statistical-based approaches and data-driven approaches. Statistical-based methods are based on particular probabilistic models of noisy speech [4], [5], such as spectral subtraction methods [6], Wiener filtering [7], and minimum mean-square error (MMSE) of the spectral amplitude [8]. Recently, datadriven approaches use deep neural networks (DNNs) to estimate the ideal ratio mask (IRM) or ideal binary mask (IBM) and have demonstrated significant performance improvement over the conventional statistical-based methods [9], [10].…”