@inproceedings{11753, abstract = {{This contribution describes a step-wise source counting algorithm to determine the number of speakers in an offline scenario. Each speaker is identified by a variational expectation maximization (VEM) algorithm for complex Watson mixture models and therefore directly yields beamforming vectors for a subsequent speech separation process. An observation selection criterion is proposed which improves the robustness of the source counting in noise. The algorithm is compared to an alternative VEM approach with Gaussian mixture models based on directions of arrival and shown to deliver improved source counting accuracy. The article concludes by extending the offline algorithm towards a low-latency online estimation of the number of active sources from the streaming input data.}}, author = {{Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)}}, keywords = {{Accuracy, Acoustics, Estimation, Mathematical model, Soruce separation, Speech, Vectors, Bayes methods, Blind source separation, Directional statistics, Number of speakers, Speaker diarization}}, pages = {{213--217}}, title = {{{Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models}}}, year = {{2014}}, } @inproceedings{11913, abstract = {{In this paper we propose to employ directional statistics in a complex vector space to approach the problem of blind speech separation in the presence of spatially correlated noise. We interpret the values of the short time Fourier transform of the microphone signals to be draws from a mixture of complex Watson distributions, a probabilistic model which naturally accounts for spatial aliasing. The parameters of the density are related to the a priori source probabilities, the power of the sources and the transfer function ratios from sources to sensors. Estimation formulas are derived for these parameters by employing the Expectation Maximization (EM) algorithm. The E-step corresponds to the estimation of the source presence probabilities for each time-frequency bin, while the M-step leads to a maximum signal-to-noise ratio (MaxSNR) beamformer in the presence of uncertainty about the source activity. Experimental results are reported for an implementation in a generalized sidelobe canceller (GSC) like spatial beamforming configuration for 3 speech sources with significant coherent noise in reverberant environments, demonstrating the usefulness of the novel modeling framework.}}, author = {{Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)}}, keywords = {{array signal processing, blind source separation, blind speech separation, complex vector space, complex Watson distribution, directional statistics, expectation-maximisation algorithm, expectation maximization algorithm, Fourier transform, Fourier transforms, generalized sidelobe canceller, interference suppression, maximum signal-to-noise ratio beamformer, microphone signal, probabilistic model, spatial aliasing, spatial beamforming configuration, speech enhancement, statistical distributions}}, pages = {{241--244}}, title = {{{Blind speech separation employing directional statistics in an Expectation Maximization framework}}}, doi = {{10.1109/ICASSP.2010.5495994}}, year = {{2010}}, }