[{"oa":"1","date_updated":"2022-01-06T06:51:08Z","date_created":"2019-07-12T05:27:34Z","author":[{"first_name":"Lukas","id":"11213","full_name":"Drude, Lukas","last_name":"Drude"},{"last_name":"Chinaev","full_name":"Chinaev, Aleksej","first_name":"Aleksej"},{"first_name":"Dang Hai","last_name":"Tran Vu","full_name":"Tran Vu, Dang Hai"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"title":"Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHa2014.pdf"}],"related_material":{"link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHa2014_Poster.pdf","relation":"supplementary_material","description":"Poster"}]},"year":"2014","citation":{"ama":"Drude L, Chinaev A, Tran Vu DH, Haeb-Umbach R. Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models. In: <i>39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>. ; 2014.","ieee":"L. Drude, A. Chinaev, D. H. Tran Vu, and R. Haeb-Umbach, “Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models,” in <i>39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>, 2014.","chicago":"Drude, Lukas, Aleksej Chinaev, Dang Hai Tran Vu, and Reinhold Haeb-Umbach. “Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models.” In <i>39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>, 2014.","bibtex":"@inproceedings{Drude_Chinaev_Tran Vu_Haeb-Umbach_2014, title={Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models}, booktitle={39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)}, author={Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2014} }","short":"L. Drude, A. Chinaev, D.H. Tran Vu, R. Haeb-Umbach, in: 39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), 2014.","mla":"Drude, Lukas, et al. “Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models.” <i>39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>, 2014.","apa":"Drude, L., Chinaev, A., Tran Vu, D. H., &#38; Haeb-Umbach, R. (2014). Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models. In <i>39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>."},"_id":"11752","user_id":"44006","department":[{"_id":"54"}],"language":[{"iso":"eng"}],"type":"conference","publication":"39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)","abstract":[{"lang":"eng","text":" \"In this contribution we derive a variational EM (VEM) algorithm for model selection in complex Watson mixture models, which have been recently proposed as a model of the distribution of normalized microphone array signals in the short-time Fourier transform domain. The VEM algorithm is applied to count the number of active sources in a speech mixture by iteratively estimating the mode vectors of the Watson distributions and suppressing the signals from the corresponding directions. A key theoretical contribution is the derivation of the MMSE estimate of a quadratic form involving the mode vector of the Watson distribution. The experimental results demonstrate the effectiveness of the source counting approach at moderately low SNR. It is further shown that the VEM algorithm is more robust w.r.t. used threshold values.\" "}],"status":"public"},{"status":"public","abstract":[{"lang":"eng","text":"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."}],"publication":"14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)","type":"conference","language":[{"iso":"eng"}],"keyword":["Accuracy","Acoustics","Estimation","Mathematical model","Soruce separation","Speech","Vectors","Bayes methods","Blind source separation","Directional statistics","Number of speakers","Speaker diarization"],"department":[{"_id":"54"}],"user_id":"44006","_id":"11753","page":"213-217","citation":{"ieee":"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.","chicago":"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.","ama":"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.","bibtex":"@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} }","short":"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.","mla":"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.","apa":"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)."},"year":"2014","related_material":{"link":[{"description":"Poster","relation":"supplementary_material","url":"https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHaeb14_Poster.pdf"}]},"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHaeb14.pdf","open_access":"1"}],"title":"Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models","author":[{"first_name":"Lukas","last_name":"Drude","id":"11213","full_name":"Drude, Lukas"},{"first_name":"Aleksej","last_name":"Chinaev","full_name":"Chinaev, Aleksej"},{"last_name":"Tran Vu","full_name":"Tran Vu, Dang Hai","first_name":"Dang Hai"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_created":"2019-07-12T05:27:35Z","oa":"1","date_updated":"2022-01-06T06:51:08Z"}]