We address the problem of direction-of-arrival DOA estimation for multiple speech sources in an enclosed environment using a single acoustic vector sensor. The challenges in such scenario include reverberation and overlapping of the source signals. In this work, we exploit low-reverberant-single-source LRSS points in the time–frequency TF domain, where a particular source is dominant with high signal-to-reverberation ratio. Unlike conventional algorithms having limitation that such potential points need to be detected at “TF-zone” level, the proposed algorithm performs LRSS detection at “TF-point” level. Therefore, for the proposed algorithm, the potential LRSS points need not be neighbors of each other within a TF zone to be detected, resulting an increased number of detected LRSS points. The detected LRSS points are further screened by an outlier removal step such that only reliable LRSS points will be used for DOA estimation. Simulations and experiments were conducted to demonstrate the effectiveness of the proposed algorithm in multisource reverberant environments.

Multisource DOA Estimation in a Reverberant Environment Using a Single Acoustic Vector Sensor

Underdetermined blind separation of overlapped speech mixtures in time-frequency domain with estimated number of sources

http://personal.ee.surrey.ac.uk/Personal/W.Wang/papers/ChenWWZA_SpeechComm_2015.pdf

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

The number of sources present in a mixture is crucial information often assumed to be known or detected by source counting. The existing methods for source counting in underdetermined blind speech separation suffer from the overlapping between sources with low W-disjoint orthogonality. To address this issue, we propose to fit the direction-of-arrival (DOA) histogram with multiple von-Mises density (VM) functions directly and form a sparse recovery problem, where all the source clusters and the sidelobes in the DOA histogram are fitted with VM functions of different spatial parameters. We also developed a formula to perform the source counting taking advantage of the values of the sparse source vector to reduce the influence of sidelobes. Experiments are carried out to evaluate the proposed source counting method, and the results show that the proposed method outperforms two well-known baseline methods.

A Source Counting Method Using Acoustic Vector Sensor Based on Sparse Modeling of DOA Histogram

Separation of multiple speech sources by recovering sparse and non-sparse components from B-format microphone recordings

Most existing speech source separation algorithms have been developed for separating sound mixtures acquired by using a conventional microphone array. In contrast, little attention has been paid to the problem of source separation using an acoustic vector sensor (AVS). We propose a new method for the separation of convolutive mixtures by incorporating the intensity vector of the acoustic field, obtained using spatially co-located microphones which carry the direction of arrival (DOA) information. The DOA cues from the intensity vector, together with the frequency bin-wise mixing vector cues, are then used to determine the probability of each time-frequency (T-F) point of the mixture being dominated by a specific source, based on the Gaussian mixture models (GMM), whose parameters are evaluated and refined iteratively using an expectation-maximization (EM) algorithm. Finally, the probability is used to derive the T-F masks for recovering the sources. The proposed method is evaluated in simulated reverberant environments in terms of signal-to-distortion ratio (SDR), giving an average improvement of approximately 1:5 dB as compared with a related T-F mask approach based on a conventional microphone setting.

Acoustic vector sensor based reverberant speech separation with probabilistic time-frequency masking

Acoustic vector sensor (AVS) based convolutive blind source separation problem has been recently addressed under the framework of probabilistic time-frequency (T-F) masking, where both the DOA and the mixing vector cues are modelled by Gaussian distributions. In this paper, we show that the distributions of these cues vary with room acoustics, such as reverberation. Motivated by this observation, we propose a mixed model of Laplacian and Gaussian distributions to provide a better fit for these cues. The parameters of the mixed model are estimated and refined iteratively by an expectation-maximization (EM) algorithm. Experiments performed on the speech mixtures in simulated room environments show that the mixed model offers an average of about 0.68 dB and 1.18 dB improvements in signal-to-distotion (SDR) over the Gaussian and Laplacian model, respectively.

/pdf/acoustic-vector-sensor-based-speech-source-separation-with-3vbvf69rr5.pdf

Xiaoyi Chen

Papers

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

Acoustic vector sensor based reverberant speech separation with probabilistic time-frequency masking

Acoustic vector sensor based speech source separation with mixed Gaussian-Laplacian distributions