Reverberant speech separation with probabilistic time–frequency masking for B-format recordings

Electrocardiographic (ECG) signals are affected by several kinds of artifacts that may hide vital signs of interest. In this study we apply independent component analysis (ICA) to isolate motion artifacts. Standard or instantaneous ICA, which is currently the most addressed ICA model within the context of artifact removal, is compared to two other ICA techniques. The first technique is a frequency domain approach to convolutive mixture separation. The second is based on temporally constrained ICA, which enables the estimation of only one component close to a particular reference signal. Performance indexes evaluate ECG complex enhancement and relevant heart rate errors. Our results show that both convolutive and constrained ICA implementations perform better than standard ICA, thus opening up a new field of application for these two methods. Moreover, statistical analysis reveals that constrained ICA and convolutive ICA do not significantly differ concerning heart rate estimation, even though the latter overcomes the former in ECG morphology recovery.

Purpose: The purpose of this study was to investigate and analyze to increase the quality and intelligibility of speech in cars. The passenger dialogue inside the car, the sound of other equipment, and a wide range of interference effects are major challenges in the task of speech separation in-car environment.Methods: Speech enhancement based on the source separation algorithm has been proposed to enhance the preferred speech signals using a microphone array inside a car. The proposed approach determines the signal direction in the time domain by utilizing the time difference of arrival (TDOA). TDOA signals are processed, and an adaptive least mean square method is used to determine the enhanced preferred signal.Results: Experimental results show that the proposed approach yields an signal-to-noise ratio (SNR) of 7.4, perceptual evaluation of speech quality (PESQ) of 2.33 respectively. The proposed strategy outperforms existing methods in terms of PESQ, and SNR. The PESQ of the proposed method is 2.45%, and 5.22% better than the existing Independent Component Analyses, and Run length Source techniques.Conclusion: Finally, compared to the existing methods, the suggested speech enhancement algorithm is more reliable and flexible, and it can properly identify the exact location of the sound.

In this paper, localization and separation of acoustic sources are examined. Depending on the number of sources in relation to the array channels, the problem is investigated in terms of underdetermined and overdetermined configurations. In the underdetermined configuration, virtual monopole sources are assumed in uniformly spaced angles. The problem is then formulated into compressive sampling (CS) problem which can be solved by using the linearly constrained -norm convex (CVX) optimization. The solution yields the directions of real sources and the source signal spectrum, which enables localization and reconstruction of sources at one shot. In the underdetermined configuration, source localization and signal separation is carried out in two steps. First, the directions of arrival (DOA) are estimated with Minimum Variance Distortionless Response (MVDR) or Multiple Signal Classification (MUSIC). Next, Tikhonov regularization (TIKR) is utilized to recover the source spectrum. In the localization problem for both configurations, Neyman-Pearson detector is employed to determine thresholds for source detection. Numerical and experimental results show that the proposed methods produce improved speech quality in terms of mean opinion score (MOS) in perceptual evaluation of speech quality (PESQ) test.

This paper presents an unsupervised method that trains neural source separation by using only multichannel mixture signals. Conventional neural separation methods require a lot of supervised data to achieve excellent performance. Although multichannel methods based on spatial information can work without such training data, they are often sensitive to parameter initialization and degraded with the sources located close to each other. The proposed method uses a cost function based on a spatial model called a complex Gaussian mixture model (cGMM). This model has the time-frequency (TF) masks and direction of arrivals (DoAs) of sources as latent variables and is used for training separation and localization networks that respectively estimate these variables. This joint training solves the frequency permutation ambiguity of the spatial model in a unified deep Bayesian framework. In addition, the pre-trained network can be used not only for conducting monaural separation but also for efficiently initializing a multichannel separation algorithm. Experimental results with simulated speech mixtures showed that our method outperformed a conventional initialization method.

We propose a new algorithm for blind source separation (BSS), in which independent component analysis (ICA) and beamforming are combined to resolve the low-convergence problem through optimization in ICA. The proposed method consists of the following three parts: (1) frequency-domain ICA with direction-of-arrival (DOA) estimation; (2) null beamforming based on the estimated DOA; (3) integration of (1) and (2) based on the algorithm diversity in both iteration and frequency domain. The inverse of the mixing matrix obtained by ICA is temporally substituted by the matrix based on null beamforming through iterative optimization, and the temporal alternation between ICA and beamforming can realize fast- and high-convergence optimization. The results of the signal separation experiments reveal that the signal separation performance of the proposed algorithm is superior to that of the conventional ICA-based BSS method, even under reverberant conditions.

This paper investigates how the directional characteristics of an Acoustic Vector Sensor (AVS) can be used to separate speech sources. The technique described in this work takes advantage of the frequency domain direction of arrival estimates to identify the location, relative to the AVS array, of each individual speaker in a group of speakers and separate them accordingly into individual speech signals. Results presented in this work show that the technique can be used for real-time separation of speech sources using a single 20ms frame of speech, furthermore the results presented show that there is an average improvement in the Signal to Interference Ratio (SIR) for the proposed algorithm over the unprocessed recording of 15.1 dB and an average improvement of 5.4 dB in terms of Signal to Distortion Ratio (SDR) over the unprocessed recordings. In addition to the SIR and SDR results, Perceptual Evaluation of Speech Quality (PESQ) and listening tests both show an improvement in perceptual quality of 1 Mean Opinion Score (MOS) over unprocessed recordings.

We propose a new algorithm for blind source separation (BSS), in which independent component analysis (ICA) and beamforming are combined to resolve the low-convergence problem through optimization in ICA. The proposed method consists of the following three parts: (1) frequency-domain ICA with direction-of-arrival (DOA) estimation, (2) null beamforming based on the estimated DOA, and (3) integration of (1) and (2) based on the algorithm diversity in both iteration and frequency domain. The inverse of the mixing matrix obtained by ICA is temporally substituted by the matrix based on null beamforming through iterative optimization, and the temporal alternation between ICA and beamforming can realize fast- and high-convergence optimization. The results of the signal separation experiments reveal that the signal separation performance of the proposed algorithm is superior to that of the conventional ICA-based BSS method, even under reverberant conditions.

Objective metrics, such as the perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and signal-to-distortion ratio (SDR), are often used for evaluating speech. These metrics are intrusive since they require a reference (clean) speech signal to complete the evaluation. The need for a reference signal reduces the practicality of these metrics, since a clean reference signal is not typically available during real-world testing. In this paper, a two-stage approach is presented that estimates the objective score of these intrusive metrics in a non-intrusive manner, which enables testing in real-world environments. More specifically, objective score estimation is treated as a machine-learning problem, and the use of speech-enhancement residuals and convolutional long short-term memory (SER-CL) networks is proposed to blindly estimate the objective scores (i.e., PESQ, STOI, and SDR) of various speech signals. The approach is evaluated in simulated and real environments that contain different combinations of noise and reverberation. The results reveal that the proposed approach is a reasonable alternative for evaluating speech, where it performs well in terms of accuracy and correlation. The proposed approach also outperforms comparison approaches in several environments.

This work addresses the solution of localizing and enhancing hands-free speech inside the car environment. Cars have different types of sounds from outside, co-passengers dialogue and noise. To provide better-quality speech, a microphone array-based beamforming technique is used. This research work proposes the method for selected source localization, source separation, and enhancement. An estimation of the direction of arrival (DOA) to localize the signal direction and preferred direction is selected for speech enhancement. The spiral and sine-cosine algorithm (SSCA) algorithm is combined with an adaptive least mean square to adapt the system for different environments. The algorithm is implemented in hardware and tested in a real-time car environment. The results showed significant improvement in signal-to-noise ratio (SNR) of 5.2 dB and perceptual evaluation of speech quality (PESQ) of 2.3. Finally, the model is fine-tuned for the car to get better quality. The proposed technique is efficient, and results are compared with existing methods.

Speech communicated is adversely affected by environmental noise. It is important to process the speech and reduce noise for better understanding. Speech enhancement or noise reduction is useful to provide comfort for human or machine listening. Traditional algorithms provide better noise reduction and better-quality speech. Due to the non-stationary nature of noise and the quasi-stationary nature of speech, the traditional methods are proven inadequate in achieving high-quality speech. Later statistical estimators based on Gaussian, and super-Gaussian Probability Density Function (PDF) assumption further improved the enhancement performance. But still, non-stationary noise nature introduces artifacts in processed signal and results in decreased performance. It is observed that neural network approaches and the factorization approach provide better performance even under non-stationary noises by proper training and large database. Different features result in variations in output performance under unseen noise and speaker conditions. It is important to understand the importance and advantages of traditional methods, statistical estimators, and neural network approaches performances. To select the suitable method for a required application, it is essential to consider the trade-off between quality and distortion. In this work, the importance of speech enhancement methods is discussed. Performance measures used for understanding the speech enhancement like Signal to Noise Ratio (SNR), Segmental SNR, Log-Likelihood Ratio (LLR), Weighted Spectral Slope (WSS), Perceptual Evaluation of Speech Quality (PESQ), Short-Time Objective Intelligibility (STOI), Signal to Distortion Ratio (SDR) and Mean Opinion Score (MOS), are given. Highlights of important results are discussed for analyzing better speech enhancement methods for the required application. In this work, performance is compared using objective and subjective performance measures. Simulation results show superior performance when neural network is employed in statistical estimators.

An improvement is proposed in the audio-visual approach to solve the problem of source separation of physically moving speakers by exploiting multiple video cameras, a circular microphone array and robust spatial beamforming. The challenge of separating moving sources is that the mixing filters are time varying; as such the unmixing filters should also be time varying but these are difficult to determine from only audio measurements. Therefore the visual modality is utilized to track the direction of each speaker to the microphone array by using a Markov chain Monte Carlo particle filter (MCMC-PF). The proposed direction of arrival (DOA) tracker improves the computational complexity with respect to a previously employed 3-D multi-speaker position tracker. The DOA information is used in a robust least squares frequency invariant data independent (RLSFIDI) beamformer to separate the audio sources. Experimental results show that the proposed technique efficiently tracks the DOA with improved computational complexity and enhanced source separation.

To address the significant performance degradation of conventional underdetermined blind source separation algorithms for frequency-hopping (FH) signals under time-frequency (TF) overlapping conditions, this brief presents a novel three-stage scheme based on the TF distribution of FH signals. In the first stage, key parameters of the FH signal are estimated using a TF binary graph. In the second step, the initial mixing matrix is estimated for non-overlapping and overlapping carrier frequencies employing density peaks clustering and tensor decomposition methods, respectively. In the third step, the final mixing matrix, directions of arrival (DOA), and source signals are estimated using the expectation-maximization algorithm within the nonnegative matrix factorization model. Finally, different segments of the FH signals are spliced together based on the DOAs of different source signals. Comprehensive experimental results demonstrate the superior performance of the proposed algorithm compared to state-of-the-art algorithms. Even at a signal-to-noise ratio of 5 dB, the correlation coefficient of the estimated source signals can still reach 0.91.

This paper proposes a speech enhancement method for non-stationary Gaussian noise based on regularized non-negative matrix factorization (NMF). The magnitudes of speech and noise are implemented by a model based in iterative posterior NMF which are applied using prior distributions in transform domain. This is used since the sample distributions of the above are well suited to Weibull and Rayleigh densities well. For the accomplishment in time-varying noise environments, both the speech and noise bases of NMF are adapted simultaneously. With the usage of estimated speech presence probability, this paper proposes to adaptively estimate the statistics of these distributions. The method in this paper gives the best results for perceptual evaluation of speech quality (PESQ) and the signal-to-distortion ratio (SDR).

Exemplar-based techniques, where the noisy speech is decomposed as a linear combination of the speech and noise exemplars stored in a dictionary, have been successfully used for speech enhancement in noisy environments. This paper extends this technique to achieve speech dereverberation in noisy environments by means of a nonnegative approximation of the noisy reverberant speech in the frequency domain. A novel approach for estimating the room impulse response (RIR) together with the speech and noise estimates using a non-negative matrix deconvolution (NMD)-based technique is proposed. In addition, we extend an existing technique based on nonnegative matrix factorisation (NMF) that performs speech derever-beration in noise-free environments to noisy scenarios. New estimators for jointly obtaining the RIR and exemplar weights for the NMD and NMF-based formulations are presented. The proposed techniques are evaluated on the noise-free and noisy reverberant speech in the CHiME-2 WSJ0 database and are shown to yield better speech enhancement in terms of signal-to-distortion ratio (SDR), perceptual evaluation of speech quality (PESQ) and cepstral distance (CD) measures.

We present a multi-microphone multi-speaker direction of arrival (DOA) tracking algorithm. In the proposed algorithm, the DOA values are discretized to a set of candidate DOAs. Accordingly, and following the W-disjoint orthogonality (WDO) property of the speech signal, each time-frequency (TF) bin in the short-time Fourier transform (STFT) domain is associated with a single DOA candidate. The conditional probability of each TF observation given its corresponding DOA association, is modeled as a multivariate complex-Gaussian distribution, with the power spectral density (PSD) of each source an unknown parameter. By applying the Fisher-Neyman factorization, it can be shown that this conditional probability is proportional to the signal-to-noise ratio (SNR) at the outputs of minimum variance distortionless response (MVDR)-beamformers (BFs), directed towards all candidate DOAs. We model these observations as either a frequency-wise parallel Hidden Markov Model (HMM) or as a coupled HMM with coupling between adjacent frequency bins. The posterior probability of these associations is inferred by applying an extended FB (FB) algorithm, and the actual DOAs can be inferred from this posterior. An experimental study demonstrates the benefits of the proposed algorithm using both a simulated dataset and real recordings drawn from the acoustic source localization and tracking (LOCATA) dataset.