We propose a novel multi-source direction of arrival (DOA) estimation technique using a convolutional neural network algorithm which learns the modal coherence patterns of an incident soundfield through measured spherical harmonic coefficients. We train our model for individual time-frequency bins in the short-time Fourier transform spectrum by analyzing the unique snapshot of modal coherence for each desired direction. The proposed method is capable of estimating simultaneously active multiple sound sources on a 3D space using a single-source training scheme. This single-source training scheme reduces the training time and resource requirements as well as allows the reuse of the same trained model for different multi-source combinations. The method is evaluated against various simulated and practical noisy and reverberant environments with varying acoustic criteria and found to outperform the baseline methods in terms of DOA estimation accuracy. Furthermore, the proposed algorithm allows independent training of azimuth and elevation during a full DOA estimation over 3D space which significantly improves its training efficiency without affecting the overall estimation accuracy.

We proposed a spatial coherence-based PSD estimation and source separation technique in [1] using a 32-channel spherical microphone array. While the proposed spherical microphone-based method exhibited a satisfactory performance in separating multiple sound sources in a reverberant environment, the use of a large number of microphones remains an issue for some practical considerations. In this paper, we investigate an alternative array structure to achieve spatial coherence-based source separation using a planar microphone array. This method is particularly useful in separating a limited number of sound sources in a mixed acoustic scene. The simplified array structure we used here can easily be integrated with many commercial acoustical instruments such as smart home devices to achieve better speech enhancements.

In this paper, we propose an efficient technique for estimating individual power spectral density (PSD) components, i.e., PSD of each desired sound source as well as of noise and reverberation, in a multisource reverberant sound scene with coherent background noise. We formulate the problem in the spherical harmonics domain to take the advantage of the inherent orthogonality of the spherical harmonics basis functions and extract the PSD components from the cross-correlation between the different sound field modes. We also investigate an implementation issue that occurs at the nulls of the Bessel functions and offer an engineering solution. The performance evaluation takes place in a practical environment with a commercial microphone array in order to measure the robustness of the proposed algorithm against all the deviations incurred in practice. We also exhibit an application of the proposed PSD estimator through a source septation algorithm and compare the performance with a contemporary method in terms of different objective measures.