In this letter, we propose a new approach to speech enhancement based on a complex Laplacian probability density function (pdf). With a use of a goodness-of-fit (GOF) test, we discover that the complex Laplacian pdf is more desirable to describe noisy speech distribution than the conventional Gaussian pdf for speech enhancement. The likelihood ratio (LR) is computed and then applied to computat...

Performance of the linear models, widely used within the framework of adaptive line enhancement (ALE), deteriorates dramatically in the presence of non-Gaussian noises. On the other hand, adaptive implementation of nonlinear models, e.g. the Volterra filters, suffers from the severe problems of large number of parameters and slow convergence. Nonetheless, kernel methods are emerging solutions t...

A noise estimation algorithm plays an important role in speech enhancement. Speech enhancement for automatic speaker recognition system, Man–Machine communication, Voice recognition systems, speech coders, Hearing aids, Video conferencing and many applications are related to speech processing. All these systems are real world systems and input available for these systems is only the noisy speec...

This paper proposes an approach based on the compressed sensing for speech enhancement. It attempts to exploit the fact that it is relatively easy to find sparse representation for speech signal but the same cannot hold true for noise. Thus for a given speech signal a sparse vector is derived which extracts the speech signal from the given noisy speech signal. Approach is further modified to en...

Traditionally, cerebellar model articulation controller (CMAC) is used in motor control, inverted pendulum robot, and nonlinear channel equalization. In this study, we investigate the capability of CMAC for speech enhancement. We construct a CMAC-based supervised speech enhancement system, which includes offline and online phases. In the offline phase, a paired noisy-clean speech dataset is pre...

This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asy...

The Dual Excitation (DE) speech model is applied to the problem of speech enhancement. The use of this model and its novel decomposition of speech into co-existing voiced and unvoiced components allow removal of additive wideband noise from the degraded speech with only the knowledge of the power spectrum of the noise. The unique properties of each component are exploited to improve the perform...

This paper presents a new research and education platform for speech processing. The platform is called Speech Enhancement for Android (SEA) and incorporates past and present speech enhancement techniques applied to recorded speech corrupted by real world noise sources. Researchers, students and teaching staff can use this platform to perform speech enhancement and observe its effects on the li...

Recently, lots of algorithms using machine learning approaches have been proposed in the speech enhancement area. One of the most well-known approaches is the non-negative matrix factorization (NMF) -based one which analyzes noisy speech with speech and noise bases. However, NMF-based algorithms have difficulties in estimating speech and noise encoding vectors when their subspaces overlap. In t...