%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 01:16:12 PM @INPROCEEDINGS{Oualil_ICASSP2013_2013, author = {Oualil, Youssef and Magimai.-Doss, Mathew and Faubel, Friedrich and Klakow, Dietrich}, projects = {Idiap, IM2, FP 7}, month = may, title = {A Probabilistic Framework for Multiple Speaker Localization}, booktitle = {Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}, year = {2013}, crossref = {Oualil_Idiap-RR-37-2012}, abstract = {This paper presents a novel probabilistic framework for localizing multiple speakers with a microphone array. In this framework, the generalized cross correlation function (GCC) of each microphone pair is interpreted as a probability distribution of the time difference of arrival (TDOA) and subsequently approximated as a Gaussian mixture. The distribution parameters are estimated with a weighted expectation maximization algorithm. Then, the joint distribution of the TDOA Gaussian mixtures is mapped to a multimodal distribution in the location space, where each mode represents a potential source location. The approach taken here performs the localization by 1) reducing the search space to some regions that are likely to contain a source and then 2) extracting the actual speaker locations with a numerical optimization algorithm. The effectiveness of the proposed approach is shown using the AV16.3 corpus.}, pdf = {https://publications.idiap.ch/attachments/papers/2013/Oualil_ICASSP2013_2013.pdf} } crossreferenced publications: @TECHREPORT{Oualil_Idiap-RR-37-2012, author = {Oualil, Youssef and Magimai.-Doss, Mathew and Faubel, Friedrich and Klakow, Dietrich}, editor = {Oualil, Youssef and Magimai.-Doss, Mathew}, keywords = {Gaussian mixture, localization, microphone arrays, multiple speakers, Steered response power}, projects = {FP 7}, month = {12}, title = {A Probabilistic Framework for Multiple Speaker Localization}, type = {Idiap-RR}, number = {Idiap-RR-37-2012}, year = {2012}, institution = {Idiap}, note = {Submitted to ICASSP'13}, abstract = {This paper presents a novel probabilistic framework for localizing multiple speakers with a microphone array. In this framework, the generalized cross correlation function (GCC) of each microphone pair is interpreted as a probability distribution of the time difference of arrival (TDOA) and subsequently approximated as a Gaussian mixture. The distribution parameters are estimated with a weighted expectation maximization algorithm. Then, the joint distribution of the TDOA Gaussian mixtures is mapped to a multimodal distribution in the location space, where each mode represents a potential source location. The approach taken here performs the localization by 1) reducing the search space to some regions that are likely to contain a source and then 2) extracting the actual speaker locations with a numerical optimization algorithm. The effectiveness of the proposed approach is shown using the AV16.3 corpus.}, pdf = {https://publications.idiap.ch/attachments/reports/2012/Oualil_Idiap-RR-37-2012.pdf} }