Tariqullah Jan

A multistage approach for blind separation of convolutive speech mixtures

In this paper, we propose a novel algorithm for the separation of convolutive speech mixtures using two-microphone recordings, based on the combination of independent component analysis (ICA) and ideal binary mask (IBM), together with a post-filtering process in the cepstral domain. Essentially, the proposed algorithm consists of three steps. First, a constrained convolutive ICA algorithm is applied to separate the source signals from two-microphone recordings. In the second step, we estimate the IBM by comparing the energy of corresponding time-frequency (T-F) units from the separated sources obtained with the convolutive ICA algorithm. The last step is to reduce musical noise caused typically by T-F masking using cepstral smoothing. The performance of the proposed approach is evaluated based on both reverberant mixtures generated using a simulated room model and real recordings. The proposed algorithm offers considerably higher efficiency, together with improved speech quality while producing similar separation performance as compared with a recent approach.

Hybrid routing scheme for Vehicular Delay Tolerant Networks

In Vehicular Delay Tolerant Networks (VDTN) connection from source to destination at any required period is not necessarily available. Therefore, the node with the message, save it in its own buffer and carry it until an opportunity comes across for forwarding. Fix nodes enhances the performance of VDTN. It helps in message storage and relaying messages. Due to mobility the bit error rate is high in mobile nodes connection but it is not considered in any of the previous routing schemes for VDTN. The connection between fix nodes will always have low bit error rate as compared to connection involving mobile nodes. All the pervious schemes are one dimensional. Environmental hindrances are not taken under consideration as well. Its effect can be both negative and positive. In this paper, a scheme titled Hybrid routing scheme is suggested to overcome the above stated problems. Features of another vehicular network called Vehicular Ad Hoc Networks (VANETs) are added to Maximum Priority (MaxProp) routing scheme for VDTN. Different propagation models of VANETs are implemented for both with and without mobile node communication for VDTN. The concept of bit error rate is also featured in Hybrid routing scheme. This makes Hybrid routing scheme two dimensional and more intelligent. The implementation and performance assessment of the proposed scheme is evaluated via Opportunistic Network Environment (ONE) Simulator. The Hybrid routing scheme outperform MaxProp in terms of the delivery probability and delivery delay.

A blind source separation approach based on IVA for convolutive speech mixtures

Here we present a new algorithm for the separation of convolutive speech observations using recordings from 2 microphones. This method is the union of independent vector analysis (IVA) and ideal binary mask (IBM), in conjunction with a post-filtering process in the cepstral domain. The proposed algorithm comprises of 3 steps. In the first step, an IVA algorithm is applied for the separation of the source signals from 2-microphone recordings. Second step is the estimation of IBM by the comparison of the energy of corresponding time-frequency (T-F) units of the segregated sources that are achieved using the IVA technique. Final step is the reduction of the musical noise by employing cepstral smoothing and such a noise is generated due to T-F masking. The signal to noise ratio (SNR) measurement has been used to evaluate the overall performance of the proposed method by employing the reverberant mixtures that are produced via simulated room model. The evaluation shows that it is more efficient and speech quality has been improved while generating similar segregation performance compared to a state-of-the-art approach.

A Novel Approach for Blind Estimation of Reverberation Time using Rayleigh Distribution Model

In this paper a blind estimation approach is proposed which directly utilizes the reverberant signal for estimating the RT (Reverberation Time).For estimation a very well-known method is used; MLE (Maximum Likelihood Estimation). Distribution of the decay rate is the core of the proposed method and can be achieved from the analysis of decay curve of the energy of the sound or from enclosure impulse response. In a pre-existing state of the art method Laplace distribution is used to model reverberation decay. The method proposed in this paper make use of the Rayleigh distribution and a spotting approach for modelling decay rate and identifying region of free decay in reverberant signal respectively. Motivation for the paper was deduced from the fact, when the reverberant speech RT falls in specific range then the signals decay rate impersonate Rayleigh distribution. On the basis of results of the experiments carried out for numerous reverberant signal it is clear that the performance and accuracy of the proposed method is better than other pre-existing methods.

A Novel Approach for Blind Estimation of Reverberation Time using Gamma Distribution Model

In this paper we proposed an unsupervised algorithm to estimate the reverberation time (RT) directly from the reverberant speech signal. For estimation process we use maximum likelihood estimation (MLE) which is a very well-known and state of the art method for estimation in the field of signal processing. All existing RT estimation methods are based on the decay rate distribution. The decay rate can be obtained either from the energy envelop decay curve analysis of noise source when it is switch off or from decay curve of impulse response of an enclosure. The analysis of a pre-existing method of reverberation time estimation is the foundation of the proposed method. In one of the state of the art method, the reverberation decay is modeled as a Laplacian distribution. In this paper, the proposed method models the reverberation decay as a Gamma distribution along with the unification of an effective technique for spotting free decay in reverberant speech. Maximum likelihood estimation technique is then used to estimate the RT from the free decays. The method was motivated by our observation that the RT of a reverberant signal when falls in specific range, then the decay rate of the signal follows Gamma distribution. Experiments are carried out on different reverberant speech signal to measure the accuracy of the suggested method. The experimental results reveal that the proposed method performs better and the accuracy is high in comparison to the state of the art method.

Statistical modeling for suppression of late reverberation with inverse filtering for early reflections

Reverberation has two pronounced components i.e. early reflections and late reverberations. A two stage algorithm was applied to tackle each reverberation module separately with an assumption of noise free environment. In the first stage of algorithm, inverse filter was estimated to reduce early reflections while the second stage predicted the late reverberation by means of long term multi-step linear prediction, after which the late reverberation were reduced through spectral subtraction. The two physical variables i.e. reverberation time and signal to noise ratio were used for quantification of reverberant and de-reverberant speech. Proposed algorithm was compared with another recent algorithm using six speech utterances and altered reverberation conditions. Significant improvement was shown by proposed algorithm.

A novel approach for blind separation dereverberation of speech mixtures using multiplestep linear predictive coding

A new method for the combination of blind separation and dereverberation of speech signals using linear convolutive mixing model is presented. The proposed algorithm consists of two parts. In the first part pre-filtering process is applied on speech mixtures to predict late reverberations by employing long-term multiple-step linear prediction (MSLP) and then these late reverberations are mitigated by using spectral subtraction (SS) technique. In the second part, a source separation technique has been applied consisting of various steps. Here in this part, first Independent component analysis (ICA) algorithm is used to separate target speech sources from sensor readings using the assumptions that sources involved in the mixing process are independent. Then by differentiating energy of individual time-frequency signatures of the separated target speech signals we compute ideal binary mask (IBM). Finally artifacts are suppressed which are normally the basis of time varying nature of IBM by means of cepstral smoothing. Simulated environment for reverberant mixtures is used to analyse the efficiency of our proposed algorithm. Simulations results evaluated in terms of signal to noise ratio (SNR) indicate a considerably enhanced quality of segregated speech as compared to a previous method.

Shrinkage based empirical mode decomposition for joint denoising and dereverberation

We propose a novel algorithm for the enhancement of noisy reverberant speech using empirical-mode-decomposition (EMD) based subband processing. The proposed algorithm is a one-microphone multistage algorithm. In the first step, noisy reverberant speech is decomposed adaptively into oscillatory components called intrinsic mode functions (IMFs) via an EMD algorithm. Denoising is then applied to selected high frequency IMFs using EMD-based minimum means-quared error (MMSE) filter, followed by spectral subtraction of the resulting denoised high-frequency IMFs and low-frequency IMFs. Finally, the enhanced speech signal is reconstructed from the processed IMFs. The method was motivated by our observation that the noise and reverberations are disproportionally distributed across the IMF components. Therefore, different levels of suppression can be applied to the additive noise and reverberation in each IMF. This leads to an improved enhancement performance as shown in comparison to a related recent approach, based on the measurements by the signal-to-noise ratio (SNR).