A robust adaptive filtering algorithm based on the convex combination of two adaptive filters under the maximum correntropy criterion (MCC) is proposed. Compared with conventional minimum mean square error (MSE) criterion-based adaptive filtering algorithm, the MCC-based algorithm shows a better robustness against impulsive interference. However, its major drawback is the conflicting requirements between convergence speed and steady-state mean square error. In this letter, we use the convex combination method to overcome the tradeoff problem. Instead of minimizing the squared error to update the mixing parameter in conventional convex combination scheme, the method of maximizing the correntropy is introduced to make the proposed algorithm more robust against impulsive interference. Additionally, we report a novel weight transfer method to further improve the tracking performance. The good performance in terms of convergence rate and steady-state mean square error is demonstrated in plant identification scenarios that include impulsive interference and abrupt changes.

In this paper, we propose a supervised single-channel speech enhancement method that combines Kullback-Leibler (KL) divergence-based non-negative matrix factorization (NMF) and a hidden Markov model (NMF-HMM). With the integration of the HMM, the temporal dynamics information of speech signals can be taken into account. This method includes a training stage and an enhancement stage. In the training stage, the sum of the Poisson distribution, leading to the KL divergence measure, is used as the observation model for each state of the HMM. This ensures that a computationally efficient multiplicative update can be used for the parameter update of this model. In the online enhancement stage, a novel minimum mean square error estimator is proposed for the NMF-HMM. This estimator can be implemented using parallel computing, reducing the time complexity. Moreover, compared to the traditional NMF-based speech enhancement methods, the experimental results show that our proposed algorithm improved the short-time objective intelligibility and perceptual evaluation of speech quality by 5% and 0.18, respectively.

Fundamental frequency is one of the most important characteristics of speech and audio signals. Harmonic modelbased fundamental frequency estimators offer a higher estimation accuracy and robustness against noise than the widely used autocorrelation-based methods. However, the traditional harmonic model-based estimators do not take the temporal smoothness of the fundamental frequency, the model order, and the voicing into account as they process each data segment independently. In this paper, a fully Bayesian fundamental frequency tracking algorithm based on the harmonic model and a first-order Markov process model is proposed. Smoothness priors are imposed on the fundamental frequencies, model orders, and voicing using first-order Markov process models. Using these Markov models, fundamental frequency estimation and voicing detection errors can be reduced. Using the harmonic model, the proposed fundamental frequency tracker has an improved robustness to noise. An analytical form of the likelihood function, which can be computed efficiently, is derived. Compared to the state-of-the-art neural network and non-parametric approaches, the proposed fundamental frequency tracking algorithm has superior performance in almost all investigated scenarios, especially in noisy conditions. For example, under 0 dB white Gaussian noise, the proposed algorithm reduces the mean absolute errors and gross errors by 15% and 20% on the Keele pitch database and 36% and 26% on sustained /a/ sounds from a database of Parkinson's disease voices. A MATLAB version of the proposed algorithm is made freely available for reproduction of the results 1 .

A method for minimising the L 1 norm relying on the convex combination of two affine projection sign algorithms is proposed. The major drawbacks of the affine projection sign type algorithms are a poor convergence rate and instability in time-variant scenarios, especially in the presence of abrupt changes. A convex combination method is used to obtain a superior performance. Instead of minimising the squared error in the conventional convex combination theory, the minimisation of the L 1 norm is introduced to offer a more robust solution in the presence of a non-Gaussian impulsive interference. The good performances in terms of the convergence rate and the steady-state error are demonstrated in a plant identification experiment that includes the impulsive noise and abrupt changes.

In this paper, we propose a speech enhancement method based on non-negative matrix factorization (NMF) techniques. NMF techniques allow us to approximate the power spectral density (PSD) of the noisy signal as a weighted linear combination of trained speech and noise basis vectors arranged as the columns of a matrix. In this work, we propose to use basis vectors that are parameterised by autoregressive (AR) coefficients. Parametric representation of the spectral basis is beneficial as it can encompass the signal characteristics like, e.g. the speech production model. It is observed that the parametric representation of basis vectors is beneficial while performing online speech enhancement in low delay scenarios.