Estimation of Source Panning Parameters and Segmentation of Stereophonic Mixtures

In this paper, we propose a method for finding the number of sources and their parameters from stereophonic mixtures. The method is based on clustering of narrowband interaural level and time differences for an unknown number of sources and uses an optimal segmentation on which the clustering is based. The parameter distribution, for both individual seg- ments and across segments that comprise the entire signal, is modelled as a Gaussian mixture. For each segment parame- ters are estimated using a minimum description length algo- rithm for mixtures based on the expectation-maximization al- gorithm. The generalized variance and degree of membership of the Gaussian components across segments is used as a ba- sis for the proposed selection of clusters amongst candidates. Simulations on synthetic and real audio shows promising re- sults for source parameter estimation and number of sources estimated across segments. The optimal segmentation shows an improvement for parameter estimation success rate, com- pared to the uniform segmentation.