Distributed Microphone Networks Research Articles

A distributed particle filter with sampling-based consensus density fusion for speaker tracking in distributed microphone networks

This paper proposes a novel distributed particle filter with sampling-based consensus density fusion for speaker tracking in distributed microphone networks (DMNs). Firstly, to combat the reverberation and ambient noise, multi-hypothesis likelihood model is applied to describe the likelihood distribution in the state-space model of speaker tracking problem. Then, the sequential importance resampling (SIR) is performed on each node to obtain the local posteriors of the state vector of the speaker. Since the non-Gaussian noise and the reverberation may make local posteriors presenting non-Gaussian and multi-modal characters, in this paper, the local posterior densities are approximated by Gaussian mixtures whose parameters are further transmitted to neighboring nodes to complete the distributed fusion based on the consensus method. We investigate a novel adaptive multiple importance sampling (AMIS) algorithm combining parallel tempering Monte Carlo (PTMC) samplers to achieve the sampling-based consensus density fusion of the non-Gaussian local posteriors and estimate the global posterior locally on each node. At last, the optimal global estimation of the speaker state vector could be calculated by using the estimated global posterior on each node in DMNs. Simulation and real-world recording experiment results show that the proposed speaker tracking method exhibits satisfactory tracking performance under reverberant and noisy environments. Moreover, it is easy and feasible to extend the proposed tracking algorithm to solve the multi-speaker tracking problem.

Low-complexity energy-aware sensor selection for noise reduction in distributed microphone networks

Noise reduction (NR) is a necessary front-end in many audio applications for improving signal quality. It was shown that sparsity-promoting sensor selection potentially makes a trade-off between energy consumption and NR performance, which is rather important for large-scale wireless acoustic sensor networks (WASNs), where many sensors contribute negligibly to NR but energy consumption affects the lifetime of WASNs. This paper presents a sensor selection approach for beamforming-based NR by minimizing the total energy consumption and constraining the output noise variance. Motivated by the optimal semi-definite programming (SDP) solution and the utility-based method, we propose three low-complexity selection metrics: weighted utility, gradient, and weighted input signal-to-noise ratio (SNR). It is shown that the proposed weighted utility and gradient-based methods are near-optimal in performance but much faster than the SDP-based method, and the weighted SNR method has the lowest time complexity with a tiny performance sacrifice. Numerical results using a simulated WASN validate the superiority of the proposed approaches over conventional methods.

Speaker tracking based on distributed particle filter and interacting multiple model in distributed microphone networks

The reverberations and Gaussian noises from indoor environments pollute speech signals and bring the degradation of speaker tracking performance. In the paper, a speaker tracking method based on the distributed particle filter (DPF) and the interacting multiple model (IMM) is proposed in distributed microphone networks. The generalized cross-correlation (GCC) function is first employed to estimate the time difference of arrival (TDOA) of speech signals received by two microphones at each node. To overcome the adverse effects of reverberation and noise, multiple TDOAs are selected to calculate the multiple-hypothesis model as the local weight of the DPF. To simulate a real speaker motion, the IMM algorithm is applied and a calculation method of the local measurement is presented based on multiple TDOAs. Finally, the speaker tracking method based on the DPF and IMM is performed to track a moving speaker and obtain a global consistent position estimate. The proposed method can track the moving speaker in reverberant and noisy environments with high tracking accuracy in distributed networks, and it is robust against the fault nodes. Simulation results demonstrate the validity of the proposed speaker tracking method.

Adaptive Frequency Response Calibration Method for Microphone Arrays

Frequency response mismatch among microphones inevitably leads to performance deterioration of signal processing algorithms of microphone arrays, especially for distributed microphone networks. An adaptive frequency response calibration method for microphone arrays based on frequency domain least mean square (FLMS) algorithm is proposed in this paper. Adaptive calibration filters are first introduced to calibrate the frequency response mismatch among microphones, which are concatenated with microphone channels. Then, the frequency response mismatch problem is formulated with a combined spectrum mean square error criterion of pairwise microphone outputs, and an unit-norm constraint is imposed to avoid undesired solutions. Finally, FLMS algorithm is used to design the calibration filter in each microphone channel. This method achieves good frequency response calibration performance even under severe ambient noise and reverberation conditions. Experimental results reveal the validity of the proposed method.

Distributed Acoustic Source Tracking in Noisy and Reverberant Environments With Distributed Microphone Networks

In this paper, an improved distributed unscented Kalman particle filter (DUKPF) is proposed for the problem of tracking a single moving acoustic source in noisy and reverberant environments with distributed microphone networks. The conventional DUKPF employs the unscented Kalman filter (UKF) for its proposal of particle sampling, whereas the UKF incorporates one single observation from a certain localization function, which is vulnerable to noise or reverberation. To alleviate this problem, multiple observations are extracted from the localization function at each node and incorporated into the state update of the UKF via the probability data association (PDA) technique, yielding the PDA-UKF. Next, employing the PDA-UKF for the proposal of particle sampling, the improved DUKPF is further developed. Finally, the improved DUKPF is adapted for the acoustic source tracking problem, and a distributed acoustic source tracking method is presented. Simulation results reveal that the improved DUKPF achieved better tracking performance than the conventional DUKPF in different noisy and reverberant conditions.

Multilevel B-Splines-Based Learning Approach for Sound Source Localization

In this paper, a new learning approach for sound source localization is presented using ad hoc either synchronous or asynchronous distributed microphone networks based on the time differences of arrival (TDOA) estimation. It is first to propose a new concept in which the coordinates of a sound source location are defined as the functions of TDOAs, computing for each pair of microphone signals in the network. Then, given a set of pre-recorded sound measurements and their corresponding source locations, the multilevel B-splines-based learning model is proposed to be trained by the input of the known TDOAs and the output of the known coordinates of the sound source locations. For a new acoustic source, if its sound signals are recorded, the correspondingly computed TDOAs can be fed into the learned model to predict the location of the new source. Superiorities of the proposed method are to incorporate the acoustic characteristics of a targeted environment and even remaining uncertainty of TDOA estimations into the learning model before conducting its prediction and to be applicable for both synchronous or asynchronous distributed microphone sensor networks. The effectiveness of the proposed algorithm in terms of localization accuracy and computational cost in comparisons with the state-of-the-art methods was extensively validated on both synthetic simulation experiments as well as in three real-life environments.

Speaker Tracking Based on Distributed Particle Filter and Iterative Covariance Intersection in Distributed Microphone Networks

Speaker tracking in distributed microphone networks is a challenging task due to the adverse effects of reverberation and noise. In this paper, a speaker tracking method based on distributed particle filter (DPF) and modified iterative covariance intersection (MICI) algorithm is proposed in distributed microphone networks. Specifically, the time difference of arrival (TDOA) of speech signals received by a pair of microphones at each node is first estimated using the generalized cross-correlation function. Next, multiple TDOAs are considered as the local measurement via a choice strategy and the multiple-hypothesis model is used as the local likelihood function of the DPF. Finally, the MICI algorithm is proposed to fuse local estimates to implement a global consistent speaker tracking where the local estimates at individual nodes are allowed to be unknown cross-correlations. The proposed method can successfully track the speaker in reverberant and noisy environments, and it is robust to the node faults and suitable to track speaker in networks with the unknown number of nodes. Simulation results demonstrate that the proposed method has better performance over the existing methods when SNR <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$&lt; $</tex-math></inline-formula> 10 dB. Real-world experiments reveal validity of the proposed method.

Acoustic source tracking based on adaptive distributed particle filter in distributed microphone networks

Abstract In this paper, an adaptive distributed particle filter (ADPF) is proposed for single acoustic source tracking in distributed microphone networks (DMNs). To deal with spurious effects due to the reverberation and noise, a modified multiple-hypothesis model is first investigated by exploiting the generalized cross-correlation (GCC) function. Based on this model, the time-delay of arrival (TDOA) selection is performed for constituting the local observation. Then the acoustic source tracking is formulated as a Bayesian filtering problem under the assumption on the Langevin dynamic model of the source motion. Next, an adaptive distributed particle filter (ADPF) is presented to solve the Bayesian filtering problem for distributed acoustic source tracking. To improve the tracking performance, in the proposed ADPF, an adaptive and distributed computation method of the optimal proposal function is designed based on the Gaussian approximation, implemented by utilizing a Markov Chain Monte Carlo (MCMC) sampler and a consensus filter. The main advantage of the proposed acoustic source tracking method is the combination of the strength of the modified TDOA multiple-hypothesis model and the ADPF. Both simulation and real-world recording experiment results show that, the proposed ADPF has a relatively good tracking performance under different SNR conditions and reverberation environments.

Distributed particle filter based speaker tracking in distributed microphone networks under non-Gaussian noise environments

Non-Gaussian noise distorts the speech signals and leads to the degradation of speaker tracking performance. In this paper, a distributed particle filter (DPF) based speaker tracking method in distributed microphone networks under non-Gaussian noise and reverberant environments is proposed. A generalized correntropy function is first presented to estimate the time differences of arrival (TDOA) for speech signals at each node in distributed microphone networks. Next, to address spurious TDOA estimations caused by noise and reverberation, a multiple-hypothesis likelihood model is introduced to calculate the local likelihood functions of the DPF. Finally, a DPF fusing local likelihood functions with an average consensus algorithm is employed to estimate a moving speaker's positions. The proposed method can accurately track the speaker under non-Gaussian noise and reverberant environments, and it is scalable and robust against the nodes failure in distributed networks. Simulation experiments show the validation of the proposed speaker tracking method.

Distributed Marginalized Auxiliary Particle Filter for Speaker Tracking in Distributed Microphone Networks

In this paper, a distributed marginalized auxiliary particle filter DMAPF is proposed for speaker tracking in distributed microphone networks. After marginalizing the state-space model, the speaker's velocity and position are estimated using the distributed Kalman filter and the distributed auxiliary particle filter APF, respectively. To overcome the adverse effects of noise and reverberation, a time difference of arrival selection scheme is presented to construct the local observation vector, based on the generalized cross-correlation function of the microphone pair signals at each node. Next, the multiple-hypothesis model is used as the local likelihood function of the DMAPF. Finally, the DMAPF is employed to estimate the time-varying positions of a moving speaker. The proposed method combines the strengths of the marginalized particle filter, APF, and distributed estimation. It can track the speaker successfully in noisy and reverberant environments. Moreover, it requires only local communication among neighboring nodes, and is scalable for speaker tracking. Experimental results reveal the validity of the proposed speaker tracking method.

Speaker Tracking Based on Distributed Particle Filter in Distributed Microphone Networks

A speaker tracking method based on a distributed particle filter (DPF) for distributed microphone networks is proposed in this paper. First, the generalized cross-correlation (GCC) function is estimated at each node. To cope with the spurious effects due to the noise or reverberation, multiple delays related to the largest local peaks of the GCC constitute the local observation. Next, based on an optimal fusion rule, a modified DPF is presented, and a modified multiple-hypothesis model is also developed as its likelihood function by incorporating the information of the GCC. Finally, the modified DPF is used to track a moving speaker with a distributed microphone network. The proposed method requires only local communication among neighboring nodes, and is robust against nodes failure. Simulation and real-world experimental results demonstrate the validity of the proposed method.

A Robust and Low-Complexity Source Localization Algorithm for Asynchronous Distributed Microphone Networks

In this paper, we propose a robust and low-complexity acoustic source localization technique based on time differences of arrival (TDOA), which addresses the scenario of distributed sensor networks in 3D environments. Network nodes are assumed to be unsynchronized, i.e., TDOAs between microphones belonging to different nodes are not available. We begin with showing how to select feasible TDOAs for each sensor node, exploiting both geometrical considerations and a characterization of the overall generalized cross correlation (GCC) shape. We then show how to localize sources in the space-range reference frame, where TDOA measurements have a clear geometrical interpretation that can be fruitfully used in the scenario of unsynchronized sensors. In this framework, in fact, the source corresponds to the apex of a hypercone passing through points described by the sole microphone positions and TDOA measurements. The localization problem is therefore approached as a hypercone fitting problem. Finally, in order to improve the robustness of the estimate, we include an outlier detection procedure based on the evaluation of the hypercone fitting residuals. A refinement of source location estimate is then performed ignoring the contributions coming from outlier measurements. A set of simulations shows the performance of individual blocks of the system, with particular focus on the effect of TDOA selection on source localization and refinement steps. Experiments on real data validate the localization algorithm in an everyday scenario, proving that good accuracy can be obtained while saving computational cost in comparison with state-of-the-art techniques.

Global Coherence Field and Distributed Particle Filter-Based Speaker Tracking in Distributed Microphone Networks

Based on the combination of global coherence field (GCF) and distributed particle filter (DPF) a speaker tracking method is proposed for distributed microphone networks in this paper. In the distributed microphone network, each node comprises a microphone pair, and its generalized cross-correlation (GCC) function is estimated. Based on the average over all local GCC observations, a global coherence field-based pseudo-likelihood (GCF-PL) function is developed as the likelihood for a DPF. In the proposed method, all nodes share an identical particle set, and each node performs local particle filtering simultaneously. In the local particle filter, the likelihood GCF-PL for each particle weight is computed with an average consensus algorithm. With an identical particle set and the consistent estimate of GCF-PL for each particle weight, all individual nodes possess a common particle presentation for the global posterior of the speaker state, which is utilized by each node for an estimated global speaker position. Employing the GCF-PL as the likelihood for DPF, no assumption is required about the independence of nodes observations as well as observation noise statistics. Additionally, only local information exchange occurs among neighboring nodes; and finally each node has a global estimate of the speaker position. Simulation results demonstrate the validity of the proposed method.

Acoustic Source Localization With Distributed Asynchronous Microphone Networks

We propose a method for localizing an acoustic source with distributed microphone networks. Time Differences of Arrival (TDOAs) of signals pertaining the same sensor are estimated through Generalized Cross-Correlation. After a TDOA filtering stage that discards measurements that are potentially unreliable, source localization is performed by minimizing a fourth-order polynomial that combines hyperbolic constraints from multiple sensors. The algorithm turns to exhibit a significantly lower computational cost compared with state-of-the-art techniques, while retaining an excellent localization accuracy in fairly reverberant conditions.

Multiple Source Localization Based on Acoustic Map De-Emphasis

This paper describes a novel approach for localization of multiple sources overlapping in time. The proposed algorithm relies on acoustic maps computed in multi-microphone settings, which are descriptions of the distribution of the acoustic activity in a monitored area. Through a proper processing of the acoustic maps, the positions of two or more simultaneously active acoustic sources can be estimated in a robust way. Experimental results obtained on real data collected for this specific task show the capabilities of the given method both with distributed microphone networks and with compact arrays.