[{"publication":"Proc. Asilomar Conference on Signals, Systems, and Computers","abstract":[{"text":"We propose a diarization system, that estimates “who spoke when” based on spatial information, to be used as a front-end of a meeting transcription system running on the signals gathered from an acoustic sensor network (ASN). Although the\r\nspatial distribution of the microphones is advantageous, exploiting the spatial diversity for diarization and signal enhancement is challenging, because the microphones’ positions are typically unknown, and the recorded signals are initially unsynchronized in general. Here, we approach these issues by first blindly synchronizing the signals and then estimating time differences of arrival (TDOAs). The TDOA information is exploited to estimate the speakers’ activity, even in the presence of multiple speakers being simultaneously active. This speaker activity information serves as a guide for a spatial mixture model, on which basis the individual speaker’s signals are extracted via beamforming. Finally, the extracted signals are forwarded to a speech recognizer. Additionally, a novel initialization scheme for spatial mixture models based on the TDOA estimates is proposed. Experiments conducted on real recordings from the LibriWASN data set have shown that our proposed system is advantageous compared to a system using a spatial mixture model, which does not make use\r\nof external diarization information.","lang":"eng"}],"file":[{"file_id":"49110","content_type":"application/pdf","relation":"main_file","date_updated":"2023-11-22T07:58:49Z","file_name":"asilomar.pdf","access_level":"open_access","file_size":212317,"date_created":"2023-11-22T07:51:18Z","creator":"schmalen"}],"date_created":"2023-11-22T07:52:29Z","type":"conference","keyword":["Diarization","time difference of arrival","ad-hoc acoustic sensor network","meeting transcription"],"department":[{"_id":"54"}],"year":"2023","title":"Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks","author":[{"full_name":"Gburrek, Tobias","last_name":"Gburrek","first_name":"Tobias","id":"44006"},{"id":"460","full_name":"Schmalenstroeer, Joerg","first_name":"Joerg","last_name":"Schmalenstroeer"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2023-11-22T07:58:49Z","language":[{"iso":"eng"}],"file_date_updated":"2023-11-22T07:58:49Z","citation":{"ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks,” presented at the 57th Asilomar Conference on Signals, Systems, and Computers, 2023.","apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2023). Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks. <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>. 57th Asilomar Conference on Signals, Systems, and Computers.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks.” In <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>, 2023.","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: Proc. Asilomar Conference on Signals, Systems, and Computers, 2023.","mla":"Gburrek, Tobias, et al. “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks.” <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>, 2023.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2023, title={Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks}, booktitle={Proc. Asilomar Conference on Signals, Systems, and Computers}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2023} }","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks. In: <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>. ; 2023."},"quality_controlled":"1","oa":"1","status":"public","conference":{"name":"57th Asilomar Conference on Signals, Systems, and Computers","start_date":"2023-10-31","end_date":"2023-11-01"},"has_accepted_license":"1","_id":"49109","user_id":"460","ddc":["004"]},{"has_accepted_license":"1","date_updated":"2022-01-06T06:56:59Z","author":[{"id":"65718","full_name":"Afifi, Haitham","last_name":"Afifi","first_name":"Haitham"},{"full_name":"Guenther, Michael","first_name":"Michael","last_name":"Guenther"},{"last_name":"Brendel","first_name":"Andreas","full_name":"Brendel, Andreas"},{"id":"126","full_name":"Karl, Holger","first_name":"Holger","last_name":"Karl"},{"first_name":"Walter","last_name":"Kellermann","full_name":"Kellermann, Walter"}],"status":"public","title":"Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities","year":"2021","user_id":"65718","ddc":["620"],"language":[{"iso":"eng"}],"_id":"25281","project":[{"name":"Akustische Sensornetzwerke - Teilprojekt \"Verteilte akustische Signalverarbeitung über funkbasierte Sensornetzwerke","_id":"27"}],"abstract":[{"lang":"eng","text":"Wireless Acoustic Sensor Networks (WASNs) have a wide range of audio signal processing applications. Due to the spatial diversity of the microphone and their relative position to the acoustic source, not all microphones are equally useful for subsequent audio signal processing tasks, nor do they all have the same wireless data transmission rates. Hence, a central task in WASNs is to balance a microphone’s estimated acoustic utility against its transmission delay, selecting a best-possible subset of microphones to record audio signals.\r\n\r\nIn this work, we use reinforcement learning to decide if a microphone should be used or switched off to maximize the acoustic quality at low transmission delays, while minimizing switching frequency. In experiments with moving sources in a simulated acoustic environment, our method outperforms naive baseline comparisons"}],"citation":{"bibtex":"@inproceedings{Afifi_Guenther_Brendel_Karl_Kellermann_2021, title={Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities}, booktitle={14. ITG Conference on Speech Communication (ITG 2021)}, author={Afifi, Haitham and Guenther, Michael and Brendel, Andreas and Karl, Holger and Kellermann, Walter}, year={2021} }","ama":"Afifi H, Guenther M, Brendel A, Karl H, Kellermann W. Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities. In: <i>14. ITG Conference on Speech Communication (ITG 2021)</i>. ; 2021.","mla":"Afifi, Haitham, et al. “Reinforcement Learning-Based Microphone Selection in Wireless Acoustic Sensor Networks Considering Network and Acoustic Utilities.” <i>14. ITG Conference on Speech Communication (ITG 2021)</i>, 2021.","chicago":"Afifi, Haitham, Michael Guenther, Andreas Brendel, Holger Karl, and Walter Kellermann. “Reinforcement Learning-Based Microphone Selection in Wireless Acoustic Sensor Networks Considering Network and Acoustic Utilities.” In <i>14. ITG Conference on Speech Communication (ITG 2021)</i>, 2021.","short":"H. Afifi, M. Guenther, A. Brendel, H. Karl, W. Kellermann, in: 14. ITG Conference on Speech Communication (ITG 2021), 2021.","ieee":"H. Afifi, M. Guenther, A. Brendel, H. Karl, and W. Kellermann, “Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities,” 2021.","apa":"Afifi, H., Guenther, M., Brendel, A., Karl, H., &#38; Kellermann, W. (2021). Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities. <i>14. ITG Conference on Speech Communication (ITG 2021)</i>."},"file_date_updated":"2021-10-04T10:58:07Z","publication":"14. ITG Conference on Speech Communication (ITG 2021)","keyword":["microphone utility","microphone selection","wireless acoustic sensor network","network delay","reinforcement learning"],"type":"conference","date_created":"2021-10-04T10:59:50Z","file":[{"file_id":"25282","success":1,"content_type":"application/pdf","file_name":"ITG_2021_paper_26 (3).pdf","file_size":283616,"access_level":"closed","relation":"main_file","date_updated":"2021-10-04T10:58:07Z","date_created":"2021-10-04T10:58:07Z","creator":"hafifi"}]},{"type":"conference","keyword":["synchronization","acoustic sensor network"],"oa":"1","department":[{"_id":"54"}],"date_created":"2019-07-12T05:30:15Z","abstract":[{"lang":"eng","text":"In this paper we present a combined hardware/software approach for synchronizing the sampling clocks of an acoustic sensor network. A first clock frequency offset estimate is obtained by a time stamp exchange protocol with a low data rate and computational requirements. The estimate is then postprocessed by a Kalman filter which exploits the specific properties of the statistics of the frequency offset estimation error. In long term experiments the deviation between the sampling oscillators of two sensor nodes never exceeded half a sample with a wired and with a wireless link between the nodes. The achieved precision enables the estimation of time difference of arrival values across different hardware devices without sharing a common sampling hardware."}],"quality_controlled":"1","related_material":{"link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2013/SchHaeb2013_Presentation.pdf","relation":"supplementary_material","description":"Presentation"}]},"publication":"21th European Signal Processing Conference (EUSIPCO 2013)","citation":{"mla":"Schmalenstroeer, Joerg, and Reinhold Haeb-Umbach. “Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model.” <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>, 2013.","bibtex":"@inproceedings{Schmalenstroeer_Haeb-Umbach_2013, title={Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model}, booktitle={21th European Signal Processing Conference (EUSIPCO 2013)}, author={Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2013} }","ama":"Schmalenstroeer J, Haeb-Umbach R. Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model. In: <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>. ; 2013.","ieee":"J. Schmalenstroeer and R. Haeb-Umbach, “Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model,” 2013.","apa":"Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2013). Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model. <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>.","chicago":"Schmalenstroeer, Joerg, and Reinhold Haeb-Umbach. “Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model.” In <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>, 2013.","short":"J. Schmalenstroeer, R. Haeb-Umbach, in: 21th European Signal Processing Conference (EUSIPCO 2013), 2013."},"user_id":"460","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2013/SchHaeb2013.pdf"}],"language":[{"iso":"eng"}],"_id":"11891","date_updated":"2023-10-26T08:11:01Z","year":"2013","title":"Sampling Rate Synchronisation in Acoustic Sensor Networks with a Pre-Trained Clock Skew Error Model","status":"public","author":[{"last_name":"Schmalenstroeer","first_name":"Joerg","full_name":"Schmalenstroeer, Joerg","id":"460"},{"id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold"}]}]