conference paper Lukas Drude author 11213 Aleksej Chinaev author Dang Hai Tran Vu author Reinhold Haeb-Umbach author 242 54 department 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. 2014 eng AccuracyAcousticsEstimationMathematical modelSoruce separationSpeechVectorsBayes methodsBlind source separationDirectional statisticsNumber of speakersSpeaker diarization 213-217 https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHaeb14_Poster.pdf Drude, Lukas, et al. “Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models.” <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)</i>, 2014, pp. 213–17. @inproceedings{Drude_Chinaev_Tran Vu_Haeb-Umbach_2014, title={Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models}, booktitle={14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)}, author={Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2014}, pages={213–217} } Drude L, Chinaev A, Tran Vu DH, Haeb-Umbach R. Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models. In: <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)</i>. ; 2014:213-217. L. Drude, A. Chinaev, D. H. Tran Vu, and R. Haeb-Umbach, “Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models,” in <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)</i>, 2014, pp. 213–217. Drude, L., Chinaev, A., Tran Vu, D. H., &#38; Haeb-Umbach, R. (2014). Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models. In <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)</i> (pp. 213–217). Drude, Lukas, Aleksej Chinaev, Dang Hai Tran Vu, and Reinhold Haeb-Umbach. “Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models.” In <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)</i>, 213–17, 2014. L. Drude, A. Chinaev, D.H. Tran Vu, R. Haeb-Umbach, in: 14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014), 2014, pp. 213–217. 117532019-07-12T05:27:35Z2022-01-06T06:51:08Z