[{"date_created":"2025-08-29T09:39:01Z","title":"Spatio-spectral diarization of meetings by combining TDOA-based  segmentation and speaker embedding-based clustering","year":"2025","external_id":{"arxiv":["2506.16228"]},"language":[{"iso":"eng"}],"ddc":["000"],"publication":"Proceedings of INTERSPEECH","file":[{"relation":"main_file","content_type":"application/pdf","file_id":"61085","access_level":"open_access","file_name":"main.pdf","file_size":921918,"creator":"cord","date_created":"2025-08-29T09:43:32Z","date_updated":"2025-08-29T09:43:32Z"}],"abstract":[{"text":"We propose a spatio-spectral, combined model-based and data-driven\r\ndiarization pipeline consisting of TDOA-based segmentation followed by\r\nembedding-based clustering. The proposed system requires neither access to\r\nmulti-channel training data nor prior knowledge about the number or placement\r\nof microphones. It works for both a compact microphone array and distributed\r\nmicrophones, with minor adjustments. Due to its superior handling of\r\noverlapping speech during segmentation, the proposed pipeline significantly\r\noutperforms the single-channel pyannote approach, both in a scenario with a\r\ncompact microphone array and in a setup with distributed microphones.\r\nAdditionally, we show that, unlike fully spatial diarization pipelines, the\r\nproposed system can correctly track speakers when they change positions.","lang":"eng"}],"author":[{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"id":"44006","full_name":"Gburrek, Tobias","last_name":"Gburrek","first_name":"Tobias"},{"id":"70272","full_name":"Deegen, Marc","last_name":"Deegen","first_name":"Marc"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-11-10T09:06:47Z","conference":{"location":"Rotterdam","name":"Interspeech 2025"},"doi":"10.21437/Interspeech.2025-1663","has_accepted_license":"1","citation":{"apa":"Cord-Landwehr, T., Gburrek, T., Deegen, M., &#38; Haeb-Umbach, R. (2025). Spatio-spectral diarization of meetings by combining TDOA-based  segmentation and speaker embedding-based clustering. <i>Proceedings of INTERSPEECH</i>. Interspeech 2025, Rotterdam. <a href=\"https://doi.org/10.21437/Interspeech.2025-1663\">https://doi.org/10.21437/Interspeech.2025-1663</a>","short":"T. Cord-Landwehr, T. Gburrek, M. Deegen, R. Haeb-Umbach, in: Proceedings of INTERSPEECH, 2025.","mla":"Cord-Landwehr, Tobias, et al. “Spatio-Spectral Diarization of Meetings by Combining TDOA-Based  Segmentation and Speaker Embedding-Based Clustering.” <i>Proceedings of INTERSPEECH</i>, 2025, doi:<a href=\"https://doi.org/10.21437/Interspeech.2025-1663\">10.21437/Interspeech.2025-1663</a>.","bibtex":"@inproceedings{Cord-Landwehr_Gburrek_Deegen_Haeb-Umbach_2025, title={Spatio-spectral diarization of meetings by combining TDOA-based  segmentation and speaker embedding-based clustering}, DOI={<a href=\"https://doi.org/10.21437/Interspeech.2025-1663\">10.21437/Interspeech.2025-1663</a>}, booktitle={Proceedings of INTERSPEECH}, author={Cord-Landwehr, Tobias and Gburrek, Tobias and Deegen, Marc and Haeb-Umbach, Reinhold}, year={2025} }","ieee":"T. Cord-Landwehr, T. Gburrek, M. Deegen, and R. Haeb-Umbach, “Spatio-spectral diarization of meetings by combining TDOA-based  segmentation and speaker embedding-based clustering,” presented at the Interspeech 2025, Rotterdam, 2025, doi: <a href=\"https://doi.org/10.21437/Interspeech.2025-1663\">10.21437/Interspeech.2025-1663</a>.","chicago":"Cord-Landwehr, Tobias, Tobias Gburrek, Marc Deegen, and Reinhold Haeb-Umbach. “Spatio-Spectral Diarization of Meetings by Combining TDOA-Based  Segmentation and Speaker Embedding-Based Clustering.” In <i>Proceedings of INTERSPEECH</i>, 2025. <a href=\"https://doi.org/10.21437/Interspeech.2025-1663\">https://doi.org/10.21437/Interspeech.2025-1663</a>.","ama":"Cord-Landwehr T, Gburrek T, Deegen M, Haeb-Umbach R. Spatio-spectral diarization of meetings by combining TDOA-based  segmentation and speaker embedding-based clustering. In: <i>Proceedings of INTERSPEECH</i>. ; 2025. doi:<a href=\"https://doi.org/10.21437/Interspeech.2025-1663\">10.21437/Interspeech.2025-1663</a>"},"user_id":"44393","department":[{"_id":"54"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"61079","file_date_updated":"2025-08-29T09:43:32Z","type":"conference","status":"public"},{"publication_status":"published","has_accepted_license":"1","quality_controlled":"1","citation":{"bibtex":"@inproceedings{Gburrek_Meise_Schmalenstroeer_Haeb-Umbach_2024, title={Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models}, DOI={<a href=\"https://doi.org/10.1109/iwaenc61483.2024.10694103\">10.1109/iwaenc61483.2024.10694103</a>}, booktitle={2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Gburrek, Tobias and Meise, Adrian Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2024} }","mla":"Gburrek, Tobias, et al. “Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models.” <i>2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, IEEE, 2024, doi:<a href=\"https://doi.org/10.1109/iwaenc61483.2024.10694103\">10.1109/iwaenc61483.2024.10694103</a>.","short":"T. Gburrek, A.T. Meise, J. Schmalenstroeer, R. Haeb-Umbach, in: 2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, 2024.","apa":"Gburrek, T., Meise, A. T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2024). Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models. <i>2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. <a href=\"https://doi.org/10.1109/iwaenc61483.2024.10694103\">https://doi.org/10.1109/iwaenc61483.2024.10694103</a>","ama":"Gburrek T, Meise AT, Schmalenstroeer J, Haeb-Umbach R. Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models. In: <i>2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE; 2024. doi:<a href=\"https://doi.org/10.1109/iwaenc61483.2024.10694103\">10.1109/iwaenc61483.2024.10694103</a>","ieee":"T. Gburrek, A. T. Meise, J. Schmalenstroeer, and R. Haeb-Umbach, “Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models,” 2024, doi: <a href=\"https://doi.org/10.1109/iwaenc61483.2024.10694103\">10.1109/iwaenc61483.2024.10694103</a>.","chicago":"Gburrek, Tobias, Adrian Tobias Meise, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models.” In <i>2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE, 2024. <a href=\"https://doi.org/10.1109/iwaenc61483.2024.10694103\">https://doi.org/10.1109/iwaenc61483.2024.10694103</a>."},"year":"2024","date_created":"2024-11-13T08:39:57Z","author":[{"first_name":"Tobias","id":"44006","full_name":"Gburrek, Tobias","last_name":"Gburrek"},{"last_name":"Meise","full_name":"Meise, Adrian Tobias","id":"79268","first_name":"Adrian Tobias"},{"first_name":"Joerg","id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"oa":"1","date_updated":"2026-01-05T16:28:23Z","publisher":"IEEE","doi":"10.1109/iwaenc61483.2024.10694103","title":"Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models","type":"conference","publication":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","file":[{"relation":"main_file","content_type":"application/pdf","access_level":"open_access","file_name":"dist_est_iwaenc24_gburrek.pdf","file_id":"57033","file_size":300589,"date_created":"2024-11-13T08:42:13Z","creator":"tgburrek","date_updated":"2024-11-13T08:42:13Z"}],"status":"public","user_id":"44006","department":[{"_id":"54"}],"_id":"57031","file_date_updated":"2024-11-13T08:42:13Z","language":[{"iso":"eng"}],"ddc":["006"]},{"citation":{"apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2023). On the Integration of Sampling Rate Synchronization and Acoustic Beamforming. <i>European Signal Processing Conference (EUSIPCO)</i>. European Signal Processing Conference (EUSIPCO), Helsinki.","mla":"Gburrek, Tobias, et al. “On the Integration of Sampling Rate Synchronization and Acoustic Beamforming.” <i>European Signal Processing Conference (EUSIPCO)</i>, 2023.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2023, title={On the Integration of Sampling Rate Synchronization and Acoustic Beamforming}, booktitle={European Signal Processing Conference (EUSIPCO)}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2023} }","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: European Signal Processing Conference (EUSIPCO), 2023.","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. On the Integration of Sampling Rate Synchronization and Acoustic Beamforming. In: <i>European Signal Processing Conference (EUSIPCO)</i>. ; 2023.","ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “On the Integration of Sampling Rate Synchronization and Acoustic Beamforming,” presented at the European Signal Processing Conference (EUSIPCO), Helsinki, 2023.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “On the Integration of Sampling Rate Synchronization and Acoustic Beamforming.” In <i>European Signal Processing Conference (EUSIPCO)</i>, 2023."},"year":"2023","quality_controlled":"1","main_file_link":[{"url":"https://eurasip.org/Proceedings/Eusipco/Eusipco2023/pdfs/0000011.pdf","open_access":"1"}],"conference":{"location":"Helsinki","name":"European Signal Processing Conference (EUSIPCO)"},"title":"On the Integration of Sampling Rate Synchronization and Acoustic Beamforming","author":[{"full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek","first_name":"Tobias"},{"last_name":"Schmalenstroeer","id":"460","full_name":"Schmalenstroeer, Joerg","first_name":"Joerg"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2023-10-18T12:54:08Z","date_updated":"2023-10-26T08:16:23Z","oa":"1","status":"public","type":"conference","publication":"European Signal Processing Conference (EUSIPCO)","language":[{"iso":"eng"}],"user_id":"460","department":[{"_id":"54"}],"_id":"48269"},{"oa":"1","date_updated":"2023-11-15T14:48:45Z","author":[{"first_name":"Joerg","id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer"},{"first_name":"Tobias","full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_created":"2023-10-18T13:00:54Z","title":"LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices","conference":{"name":"ITG Conference on Speech Communication","location":"Aachen"},"has_accepted_license":"1","quality_controlled":"1","year":"2023","citation":{"apa":"Schmalenstroeer, J., Gburrek, T., &#38; Haeb-Umbach, R. (2023). LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices. <i>ITG Conference on Speech Communication</i>. ITG Conference on Speech Communication, Aachen.","bibtex":"@inproceedings{Schmalenstroeer_Gburrek_Haeb-Umbach_2023, title={LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices}, booktitle={ITG Conference on Speech Communication}, author={Schmalenstroeer, Joerg and Gburrek, Tobias and Haeb-Umbach, Reinhold}, year={2023} }","short":"J. Schmalenstroeer, T. Gburrek, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2023.","mla":"Schmalenstroeer, Joerg, et al. “LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices.” <i>ITG Conference on Speech Communication</i>, 2023.","ama":"Schmalenstroeer J, Gburrek T, Haeb-Umbach R. LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices. In: <i>ITG Conference on Speech Communication</i>. ; 2023.","chicago":"Schmalenstroeer, Joerg, Tobias Gburrek, and Reinhold Haeb-Umbach. “LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices.” In <i>ITG Conference on Speech Communication</i>, 2023.","ieee":"J. Schmalenstroeer, T. Gburrek, and R. Haeb-Umbach, “LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices,” presented at the ITG Conference on Speech Communication, Aachen, 2023."},"_id":"48270","department":[{"_id":"54"}],"user_id":"460","ddc":["004"],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-15T14:48:44Z","publication":"ITG Conference on Speech Communication","type":"conference","status":"public","file":[{"date_updated":"2023-11-15T14:48:44Z","date_created":"2023-10-26T08:20:15Z","creator":"schmalen","file_size":2844502,"access_level":"open_access","file_id":"48483","file_name":"SchTgbHaeb2023Final.pdf","content_type":"application/pdf","relation":"main_file"}]},{"year":"2023","quality_controlled":"1","title":"Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks","date_created":"2023-11-22T07:52:29Z","file":[{"content_type":"application/pdf","relation":"main_file","creator":"schmalen","date_created":"2023-11-22T07:51:18Z","date_updated":"2023-11-22T07:58:49Z","file_name":"asilomar.pdf","access_level":"open_access","file_id":"49110","file_size":212317}],"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"}],"publication":"Proc. Asilomar Conference on Signals, Systems, and Computers","language":[{"iso":"eng"}],"keyword":["Diarization","time difference of arrival","ad-hoc acoustic sensor network","meeting transcription"],"ddc":["004"],"citation":{"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.","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.","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.","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.","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} }","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: Proc. Asilomar Conference on Signals, Systems, and Computers, 2023."},"has_accepted_license":"1","conference":{"name":"57th Asilomar Conference on Signals, Systems, and Computers","start_date":"2023-10-31","end_date":"2023-11-01"},"author":[{"first_name":"Tobias","id":"44006","full_name":"Gburrek, Tobias","last_name":"Gburrek"},{"last_name":"Schmalenstroeer","id":"460","full_name":"Schmalenstroeer, Joerg","first_name":"Joerg"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"oa":"1","date_updated":"2023-11-22T07:58:49Z","status":"public","type":"conference","file_date_updated":"2023-11-22T07:58:49Z","department":[{"_id":"54"}],"user_id":"460","_id":"49109"},{"doi":"10.1109/iwcmc55113.2022.9824980","title":"Data-driven Time Synchronization in Wireless Multimedia Networks","date_created":"2022-10-18T09:24:17Z","author":[{"first_name":"Haitham","full_name":"Afifi, Haitham","last_name":"Afifi"},{"last_name":"Karl","full_name":"Karl, Holger","first_name":"Holger"},{"id":"44006","full_name":"Gburrek, Tobias","last_name":"Gburrek","first_name":"Tobias"},{"id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer","first_name":"Joerg"}],"date_updated":"2023-10-26T08:16:07Z","publisher":"IEEE","citation":{"short":"H. Afifi, H. Karl, T. Gburrek, J. Schmalenstroeer, in: 2022 International Wireless Communications and Mobile Computing (IWCMC), IEEE, 2022.","mla":"Afifi, Haitham, et al. “Data-Driven Time Synchronization in Wireless Multimedia Networks.” <i>2022 International Wireless Communications and Mobile Computing (IWCMC)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/iwcmc55113.2022.9824980\">10.1109/iwcmc55113.2022.9824980</a>.","bibtex":"@inproceedings{Afifi_Karl_Gburrek_Schmalenstroeer_2022, title={Data-driven Time Synchronization in Wireless Multimedia Networks}, DOI={<a href=\"https://doi.org/10.1109/iwcmc55113.2022.9824980\">10.1109/iwcmc55113.2022.9824980</a>}, booktitle={2022 International Wireless Communications and Mobile Computing (IWCMC)}, publisher={IEEE}, author={Afifi, Haitham and Karl, Holger and Gburrek, Tobias and Schmalenstroeer, Joerg}, year={2022} }","apa":"Afifi, H., Karl, H., Gburrek, T., &#38; Schmalenstroeer, J. (2022). Data-driven Time Synchronization in Wireless Multimedia Networks. <i>2022 International Wireless Communications and Mobile Computing (IWCMC)</i>. <a href=\"https://doi.org/10.1109/iwcmc55113.2022.9824980\">https://doi.org/10.1109/iwcmc55113.2022.9824980</a>","ama":"Afifi H, Karl H, Gburrek T, Schmalenstroeer J. Data-driven Time Synchronization in Wireless Multimedia Networks. In: <i>2022 International Wireless Communications and Mobile Computing (IWCMC)</i>. IEEE; 2022. doi:<a href=\"https://doi.org/10.1109/iwcmc55113.2022.9824980\">10.1109/iwcmc55113.2022.9824980</a>","ieee":"H. Afifi, H. Karl, T. Gburrek, and J. Schmalenstroeer, “Data-driven Time Synchronization in Wireless Multimedia Networks,” 2022, doi: <a href=\"https://doi.org/10.1109/iwcmc55113.2022.9824980\">10.1109/iwcmc55113.2022.9824980</a>.","chicago":"Afifi, Haitham, Holger Karl, Tobias Gburrek, and Joerg Schmalenstroeer. “Data-Driven Time Synchronization in Wireless Multimedia Networks.” In <i>2022 International Wireless Communications and Mobile Computing (IWCMC)</i>. IEEE, 2022. <a href=\"https://doi.org/10.1109/iwcmc55113.2022.9824980\">https://doi.org/10.1109/iwcmc55113.2022.9824980</a>."},"year":"2022","quality_controlled":"1","publication_status":"published","language":[{"iso":"eng"}],"department":[{"_id":"54"}],"user_id":"460","_id":"33806","status":"public","publication":"2022 International Wireless Communications and Mobile Computing (IWCMC)","type":"conference"},{"doi":"10.1109/icassp43922.2022.9746284","date_updated":"2023-11-17T06:39:28Z","oa":"1","author":[{"first_name":"Tobias","last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006"},{"full_name":"Schmalenstroeer, Joerg","id":"460","last_name":"Schmalenstroeer","first_name":"Joerg"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"citation":{"ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes,” 2022, doi: <a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes.” In <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2022. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">https://doi.org/10.1109/icassp43922.2022.9746284</a>.","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes. In: <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2022. doi:<a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2022, title={On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes}, DOI={<a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2022} }","mla":"Gburrek, Tobias, et al. “On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes.” <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>.","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022.","apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2022). On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes. <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">https://doi.org/10.1109/icassp43922.2022.9746284</a>"},"publication_status":"published","has_accepted_license":"1","file_date_updated":"2023-11-17T06:39:04Z","_id":"33807","user_id":"44006","department":[{"_id":"54"}],"status":"public","type":"conference","title":"On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes","publisher":"IEEE","date_created":"2022-10-18T09:25:51Z","year":"2022","quality_controlled":"1","ddc":["004"],"language":[{"iso":"eng"}],"file":[{"date_updated":"2023-11-17T06:39:04Z","creator":"tgburrek","date_created":"2023-11-17T06:39:04Z","file_size":358015,"file_name":"gburrek_icassp22.pdf","access_level":"open_access","file_id":"48990","content_type":"application/pdf","relation":"main_file"}],"publication":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"ddc":["004"],"language":[{"iso":"eng"}],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","file":[{"date_updated":"2023-11-17T06:40:40Z","date_created":"2023-11-17T06:40:40Z","creator":"tgburrek","file_size":266475,"file_name":"iwaenc_22_camera_ready_ieee_check.pdf","access_level":"open_access","file_id":"48991","content_type":"application/pdf","relation":"main_file"}],"publisher":"IEEE","date_created":"2022-10-18T09:30:24Z","title":"Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription","quality_controlled":"1","year":"2022","_id":"33808","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"54"}],"user_id":"44006","file_date_updated":"2023-11-17T06:40:40Z","type":"conference","status":"public","oa":"1","date_updated":"2023-11-17T06:40:58Z","author":[{"last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006","first_name":"Tobias"},{"first_name":"Joerg","id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer"},{"last_name":"Heitkaemper","full_name":"Heitkaemper, Jens","id":"27643","first_name":"Jens"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"doi":"10.1109/IWAENC53105.2022.9914772","conference":{"end_date":"2022-09-08","location":" Bamberg, Germany ","name":"17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022)","start_date":"2022-09-05"},"has_accepted_license":"1","citation":{"apa":"Gburrek, T., Schmalenstroeer, J., Heitkaemper, J., &#38; Haeb-Umbach, R. (2022). Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription. <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022),  Bamberg, Germany . <a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">https://doi.org/10.1109/IWAENC53105.2022.9914772</a>","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Heitkaemper_Haeb-Umbach_2022, title={Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription}, DOI={<a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>}, booktitle={2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Heitkaemper, Jens and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. Gburrek, J. Schmalenstroeer, J. Heitkaemper, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, 2022.","mla":"Gburrek, Tobias, et al. “Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription.” <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, Jens Heitkaemper, and Reinhold Haeb-Umbach. “Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE, 2022. <a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">https://doi.org/10.1109/IWAENC53105.2022.9914772</a>.","ieee":"T. Gburrek, J. Schmalenstroeer, J. Heitkaemper, and R. Haeb-Umbach, “Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription,” presented at the 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022),  Bamberg, Germany , 2022, doi: <a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>.","ama":"Gburrek T, Schmalenstroeer J, Heitkaemper J, Haeb-Umbach R. Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE; 2022. doi:<a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>"}},{"type":"misc","status":"public","file":[{"file_size":199006,"file_name":"meeting_transcription_22.pdf","access_level":"open_access","file_id":"48992","date_updated":"2023-11-17T06:42:04Z","creator":"tgburrek","date_created":"2023-11-17T06:42:04Z","relation":"main_file","content_type":"application/pdf"}],"_id":"33816","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"448568305","_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"department":[{"_id":"54"}],"user_id":"40767","ddc":["004"],"file_date_updated":"2023-11-17T06:42:04Z","language":[{"iso":"eng"}],"has_accepted_license":"1","year":"2022","citation":{"apa":"Gburrek, T., Boeddeker, C., von Neumann, T., Cord-Landwehr, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2022). <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv. <a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">https://doi.org/10.48550/ARXIV.2205.00944</a>","mla":"Gburrek, Tobias, et al. <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv, 2022, doi:<a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">10.48550/ARXIV.2205.00944</a>.","bibtex":"@book{Gburrek_Boeddeker_von Neumann_Cord-Landwehr_Schmalenstroeer_Haeb-Umbach_2022, title={A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network}, DOI={<a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">10.48550/ARXIV.2205.00944</a>}, publisher={arXiv}, author={Gburrek, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Cord-Landwehr, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer, R. Haeb-Umbach, A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network, arXiv, 2022.","ama":"Gburrek T, Boeddeker C, von Neumann T, Cord-Landwehr T, Schmalenstroeer J, Haeb-Umbach R. <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv; 2022. doi:<a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">10.48550/ARXIV.2205.00944</a>","chicago":"Gburrek, Tobias, Christoph Boeddeker, Thilo von Neumann, Tobias Cord-Landwehr, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv, 2022. <a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">https://doi.org/10.48550/ARXIV.2205.00944</a>.","ieee":"T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer, and R. Haeb-Umbach, <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv, 2022."},"date_updated":"2025-02-12T09:03:42Z","publisher":"arXiv","oa":"1","author":[{"id":"44006","full_name":"Gburrek, Tobias","last_name":"Gburrek","first_name":"Tobias"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Tobias","last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393"},{"first_name":"Joerg","last_name":"Schmalenstroeer","full_name":"Schmalenstroeer, Joerg","id":"460"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2022-10-18T11:10:58Z","title":"A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network","doi":"10.48550/ARXIV.2205.00944"},{"language":[{"iso":"eng"}],"_id":"22528","department":[{"_id":"54"}],"user_id":"44006","abstract":[{"text":"Due to the ad hoc nature of wireless acoustic sensor networks, the position of the sensor nodes is typically unknown. This contribution proposes a technique to estimate the position and orientation of the sensor nodes from the recorded speech signals. The method assumes that a node comprises a microphone array with synchronously sampled microphones rather than a single microphone, but does not require the sampling clocks of the nodes to be synchronized. From the observed audio signals, the distances between the acoustic sources and arrays, as well as the directions of arrival, are estimated. They serve as input to a non-linear least squares problem, from which both the sensor nodes’ positions and orientations, as well as the source positions, are alternatingly estimated in an iterative process. Given one set of unknowns, i.e., either the source positions or the sensor nodes’ geometry, the other set of unknowns can be computed in closed-form. The proposed approach is computationally efficient and the first one, which employs both distance and directional information for geometry calibration in a common cost function. Since both distance and direction of arrival measurements suffer from outliers, e.g., caused by strong reflections of the sound waves on the surfaces of the room, we introduce measures to deemphasize or remove unreliable measurements. Additionally, we discuss modifications of our previously proposed deep neural network-based acoustic distance estimator, to account not only for omnidirectional sources but also for directional sources. Simulation results show good positioning accuracy and compare very favorably with alternative approaches from the literature.","lang":"eng"}],"status":"public","publication":"EURASIP Journal on Audio, Speech, and Music Processing","type":"journal_article","title":"Geometry calibration in wireless acoustic sensor networks utilizing DoA and distance information","doi":"10.1186/s13636-021-00210-x","main_file_link":[{"open_access":"1","url":"https://asmp-eurasipjournals.springeropen.com/articles/10.1186/s13636-021-00210-x"}],"oa":"1","date_updated":"2023-11-17T06:36:17Z","date_created":"2021-07-05T05:30:15Z","author":[{"first_name":"Tobias","last_name":"Gburrek","id":"44006","full_name":"Gburrek, Tobias"},{"first_name":"Joerg","id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"year":"2021","citation":{"ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. Geometry calibration in wireless acoustic sensor networks utilizing DoA and distance information. <i>EURASIP Journal on Audio, Speech, and Music Processing</i>. Published online 2021. doi:<a href=\"https://doi.org/10.1186/s13636-021-00210-x\">10.1186/s13636-021-00210-x</a>","ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “Geometry calibration in wireless acoustic sensor networks utilizing DoA and distance information,” <i>EURASIP Journal on Audio, Speech, and Music Processing</i>, 2021, doi: <a href=\"https://doi.org/10.1186/s13636-021-00210-x\">10.1186/s13636-021-00210-x</a>.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Geometry Calibration in Wireless Acoustic Sensor Networks Utilizing DoA and Distance Information.” <i>EURASIP Journal on Audio, Speech, and Music Processing</i>, 2021. <a href=\"https://doi.org/10.1186/s13636-021-00210-x\">https://doi.org/10.1186/s13636-021-00210-x</a>.","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, EURASIP Journal on Audio, Speech, and Music Processing (2021).","bibtex":"@article{Gburrek_Schmalenstroeer_Haeb-Umbach_2021, title={Geometry calibration in wireless acoustic sensor networks utilizing DoA and distance information}, DOI={<a href=\"https://doi.org/10.1186/s13636-021-00210-x\">10.1186/s13636-021-00210-x</a>}, journal={EURASIP Journal on Audio, Speech, and Music Processing}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2021} }","mla":"Gburrek, Tobias, et al. “Geometry Calibration in Wireless Acoustic Sensor Networks Utilizing DoA and Distance Information.” <i>EURASIP Journal on Audio, Speech, and Music Processing</i>, 2021, doi:<a href=\"https://doi.org/10.1186/s13636-021-00210-x\">10.1186/s13636-021-00210-x</a>.","apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2021). Geometry calibration in wireless acoustic sensor networks utilizing DoA and distance information. <i>EURASIP Journal on Audio, Speech, and Music Processing</i>. <a href=\"https://doi.org/10.1186/s13636-021-00210-x\">https://doi.org/10.1186/s13636-021-00210-x</a>"},"quality_controlled":"1","publication_identifier":{"issn":["1687-4722"]},"publication_status":"published"},{"date_updated":"2023-11-17T06:30:12Z","oa":"1","author":[{"first_name":"Tobias","last_name":"Gburrek","id":"44006","full_name":"Gburrek, Tobias"},{"first_name":"Joerg","last_name":"Schmalenstroeer","full_name":"Schmalenstroeer, Joerg","id":"460"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_created":"2021-09-09T08:30:16Z","title":"Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks","doi":"10.1109/icassp39728.2021.9413831","quality_controlled":"1","has_accepted_license":"1","publication_status":"published","year":"2021","citation":{"short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2021, title={Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks}, DOI={<a href=\"https://doi.org/10.1109/icassp39728.2021.9413831\">10.1109/icassp39728.2021.9413831</a>}, booktitle={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2021} }","mla":"Gburrek, Tobias, et al. “Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks.” <i>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2021, doi:<a href=\"https://doi.org/10.1109/icassp39728.2021.9413831\">10.1109/icassp39728.2021.9413831</a>.","apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2021). Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks. <i>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp39728.2021.9413831\">https://doi.org/10.1109/icassp39728.2021.9413831</a>","ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks,” 2021, doi: <a href=\"https://doi.org/10.1109/icassp39728.2021.9413831\">10.1109/icassp39728.2021.9413831</a>.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks.” In <i>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2021. <a href=\"https://doi.org/10.1109/icassp39728.2021.9413831\">https://doi.org/10.1109/icassp39728.2021.9413831</a>.","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks. In: <i>ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2021. doi:<a href=\"https://doi.org/10.1109/icassp39728.2021.9413831\">10.1109/icassp39728.2021.9413831</a>"},"_id":"23994","department":[{"_id":"54"}],"user_id":"44006","ddc":["004"],"file_date_updated":"2023-11-17T06:30:11Z","language":[{"iso":"eng"}],"publication":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","type":"conference","status":"public","file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2023-11-17T06:30:11Z","date_created":"2023-11-17T06:29:40Z","creator":"tgburrek","file_size":312400,"file_id":"48988","file_name":"icassp21.pdf","access_level":"open_access"}]},{"ddc":["004"],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-17T06:31:37Z","_id":"23999","department":[{"_id":"54"}],"user_id":"44006","status":"public","file":[{"date_updated":"2023-11-17T06:31:37Z","date_created":"2023-11-17T06:31:37Z","creator":"tgburrek","file_size":449694,"file_id":"48989","access_level":"open_access","file_name":"dist_est.pdf","content_type":"application/pdf","relation":"main_file"}],"publication":"Speech Communication; 14th ITG-Symposium","type":"conference","title":"On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks","date_updated":"2023-11-17T06:32:20Z","oa":"1","author":[{"last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006","first_name":"Tobias"},{"first_name":"Joerg","full_name":"Schmalenstroeer, Joerg","id":"460","last_name":"Schmalenstroeer"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_created":"2021-09-09T08:40:44Z","year":"2021","page":"1-5","citation":{"short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: Speech Communication; 14th ITG-Symposium, 2021, pp. 1–5.","mla":"Gburrek, Tobias, et al. “On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks.” <i>Speech Communication; 14th ITG-Symposium</i>, 2021, pp. 1–5.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2021, title={On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks}, booktitle={Speech Communication; 14th ITG-Symposium}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2021}, pages={1–5} }","apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2021). On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks. <i>Speech Communication; 14th ITG-Symposium</i>, 1–5.","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks. In: <i>Speech Communication; 14th ITG-Symposium</i>. ; 2021:1-5.","ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks,” in <i>Speech Communication; 14th ITG-Symposium</i>, 2021, pp. 1–5.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks.” In <i>Speech Communication; 14th ITG-Symposium</i>, 1–5, 2021."},"has_accepted_license":"1","quality_controlled":"1"},{"type":"conference","publication":"29th European Signal Processing Conference (EUSIPCO)","status":"public","user_id":"44006","department":[{"_id":"54"}],"_id":"23997","language":[{"iso":"eng"}],"quality_controlled":"1","citation":{"apa":"Chinaev, A., Enzner, G., Gburrek, T., &#38; Schmalenstroeer, J. (2021). Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss. <i>29th European Signal Processing Conference (EUSIPCO)</i>, 1–5.","short":"A. Chinaev, G. Enzner, T. Gburrek, J. Schmalenstroeer, in: 29th European Signal Processing Conference (EUSIPCO), 2021, pp. 1–5.","bibtex":"@inproceedings{Chinaev_Enzner_Gburrek_Schmalenstroeer_2021, title={Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss}, booktitle={29th European Signal Processing Conference (EUSIPCO)}, author={Chinaev, Aleksej and Enzner, Gerald and Gburrek, Tobias and Schmalenstroeer, Joerg}, year={2021}, pages={1–5} }","mla":"Chinaev, Aleksej, et al. “Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss.” <i>29th European Signal Processing Conference (EUSIPCO)</i>, 2021, pp. 1–5.","ama":"Chinaev A, Enzner G, Gburrek T, Schmalenstroeer J. Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss. In: <i>29th European Signal Processing Conference (EUSIPCO)</i>. ; 2021:1-5.","ieee":"A. Chinaev, G. Enzner, T. Gburrek, and J. Schmalenstroeer, “Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss,” in <i>29th European Signal Processing Conference (EUSIPCO)</i>, 2021, pp. 1–5.","chicago":"Chinaev, Aleksej, Gerald Enzner, Tobias Gburrek, and Joerg Schmalenstroeer. “Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss.” In <i>29th European Signal Processing Conference (EUSIPCO)</i>, 1–5, 2021."},"page":"1-5","year":"2021","date_created":"2021-09-09T08:39:06Z","author":[{"full_name":"Chinaev, Aleksej","last_name":"Chinaev","first_name":"Aleksej"},{"last_name":"Enzner","full_name":"Enzner, Gerald","first_name":"Gerald"},{"first_name":"Tobias","full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek"},{"first_name":"Joerg","full_name":"Schmalenstroeer, Joerg","id":"460","last_name":"Schmalenstroeer"}],"oa":"1","date_updated":"2023-11-17T06:37:10Z","main_file_link":[{"open_access":"1","url":"https://eurasip.org/Proceedings/Eusipco/Eusipco2021/pdfs/0001110.pdf"}],"title":"Online Estimation of Sampling Rate Offsets in Wireless Acoustic Sensor Networks with Packet Loss"},{"year":"2020","citation":{"ama":"Gburrek T, Schmalenstroeer J, Brendel A, Kellermann W, Haeb-Umbach R. Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network. In: <i>European Signal Processing Conference (EUSIPCO)</i>. ; 2020.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, Andreas Brendel, Walter Kellermann, and Reinhold Haeb-Umbach. “Deep Neural Network Based Distance Estimation for Geometry Calibration in Acoustic Sensor Network.” In <i>European Signal Processing Conference (EUSIPCO)</i>, 2020.","ieee":"T. Gburrek, J. Schmalenstroeer, A. Brendel, W. Kellermann, and R. Haeb-Umbach, “Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network,” 2020.","apa":"Gburrek, T., Schmalenstroeer, J., Brendel, A., Kellermann, W., &#38; Haeb-Umbach, R. (2020). Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network. <i>European Signal Processing Conference (EUSIPCO)</i>.","mla":"Gburrek, Tobias, et al. “Deep Neural Network Based Distance Estimation for Geometry Calibration in Acoustic Sensor Network.” <i>European Signal Processing Conference (EUSIPCO)</i>, 2020.","short":"T. Gburrek, J. Schmalenstroeer, A. Brendel, W. Kellermann, R. Haeb-Umbach, in: European Signal Processing Conference (EUSIPCO), 2020.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Brendel_Kellermann_Haeb-Umbach_2020, title={Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network}, booktitle={European Signal Processing Conference (EUSIPCO)}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Brendel, Andreas and Kellermann, Walter and Haeb-Umbach, Reinhold}, year={2020} }"},"quality_controlled":"1","has_accepted_license":"1","title":"Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network","date_updated":"2023-11-17T06:23:39Z","oa":"1","date_created":"2020-08-31T07:20:57Z","author":[{"last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006","first_name":"Tobias"},{"first_name":"Joerg","full_name":"Schmalenstroeer, Joerg","id":"460","last_name":"Schmalenstroeer"},{"full_name":"Brendel, Andreas","last_name":"Brendel","first_name":"Andreas"},{"full_name":"Kellermann, Walter","last_name":"Kellermann","first_name":"Walter"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"abstract":[{"lang":"eng","text":"We present an approach to deep neural network based (DNN-based) distance estimation in reverberant rooms for supporting geometry calibration tasks in wireless acoustic sensor networks. Signal diffuseness information from acoustic signals is aggregated via the coherent-to-diffuse power ratio to obtain a distance-related feature, which is mapped to a source-to-microphone distance estimate by means of a DNN. This information is then combined with direction-of-arrival estimates from compact microphone arrays to infer the geometry of the sensor network. Unlike many other approaches to geometry calibration, the proposed scheme does only require that the sampling clocks of the sensor nodes are roughly synchronized. In simulations we show that the proposed DNN-based distance estimator generalizes to unseen acoustic environments and that precise estimates of the sensor node positions are obtained. "}],"status":"public","file":[{"date_created":"2023-11-17T06:21:40Z","creator":"tgburrek","date_updated":"2023-11-17T06:21:40Z","access_level":"open_access","file_id":"48987","file_name":"Gburrek2020.pdf","file_size":292159,"content_type":"application/pdf","relation":"main_file"}],"publication":"European Signal Processing Conference (EUSIPCO)","type":"conference","ddc":["004"],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-17T06:21:40Z","_id":"18651","department":[{"_id":"54"}],"user_id":"44006"},{"title":"Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion","main_file_link":[{"open_access":"1","url":"https://www.isca-speech.org/archive/pdfs/ssw_2019/gburrek19_ssw.pdf"}],"conference":{"location":"Vienna","name":"10th ISCA Speech Synthesis Workshop"},"doi":"10.21437/SSW.2019-15","date_updated":"2023-11-17T06:20:39Z","oa":"1","date_created":"2019-12-04T08:12:29Z","author":[{"id":"44006","full_name":"Gburrek, Tobias","last_name":"Gburrek","first_name":"Tobias"},{"first_name":"Thomas","last_name":"Glarner","full_name":"Glarner, Thomas","id":"14169"},{"first_name":"Janek","last_name":"Ebbers","id":"34851","full_name":"Ebbers, Janek"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"first_name":"Petra","full_name":"Wagner, Petra","last_name":"Wagner"}],"year":"2019","citation":{"apa":"Gburrek, T., Glarner, T., Ebbers, J., Haeb-Umbach, R., &#38; Wagner, P. (2019). Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion. <i>Proc. 10th ISCA Speech Synthesis Workshop</i>, 81–86. <a href=\"https://doi.org/10.21437/SSW.2019-15\">https://doi.org/10.21437/SSW.2019-15</a>","mla":"Gburrek, Tobias, et al. “Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion.” <i>Proc. 10th ISCA Speech Synthesis Workshop</i>, 2019, pp. 81–86, doi:<a href=\"https://doi.org/10.21437/SSW.2019-15\">10.21437/SSW.2019-15</a>.","short":"T. Gburrek, T. Glarner, J. Ebbers, R. Haeb-Umbach, P. Wagner, in: Proc. 10th ISCA Speech Synthesis Workshop, 2019, pp. 81–86.","bibtex":"@inproceedings{Gburrek_Glarner_Ebbers_Haeb-Umbach_Wagner_2019, title={Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion}, DOI={<a href=\"https://doi.org/10.21437/SSW.2019-15\">10.21437/SSW.2019-15</a>}, booktitle={Proc. 10th ISCA Speech Synthesis Workshop}, author={Gburrek, Tobias and Glarner, Thomas and Ebbers, Janek and Haeb-Umbach, Reinhold and Wagner, Petra}, year={2019}, pages={81–86} }","ieee":"T. Gburrek, T. Glarner, J. Ebbers, R. Haeb-Umbach, and P. Wagner, “Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion,” in <i>Proc. 10th ISCA Speech Synthesis Workshop</i>, Vienna, 2019, pp. 81–86, doi: <a href=\"https://doi.org/10.21437/SSW.2019-15\">10.21437/SSW.2019-15</a>.","chicago":"Gburrek, Tobias, Thomas Glarner, Janek Ebbers, Reinhold Haeb-Umbach, and Petra Wagner. “Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion.” In <i>Proc. 10th ISCA Speech Synthesis Workshop</i>, 81–86, 2019. <a href=\"https://doi.org/10.21437/SSW.2019-15\">https://doi.org/10.21437/SSW.2019-15</a>.","ama":"Gburrek T, Glarner T, Ebbers J, Haeb-Umbach R, Wagner P. Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion. In: <i>Proc. 10th ISCA Speech Synthesis Workshop</i>. ; 2019:81-86. doi:<a href=\"https://doi.org/10.21437/SSW.2019-15\">10.21437/SSW.2019-15</a>"},"page":"81-86","quality_controlled":"1","related_material":{"link":[{"relation":"supplementary_material","description":"Listening examples","url":"http://go.upb.de/vcex"}]},"language":[{"iso":"eng"}],"_id":"15237","user_id":"44006","department":[{"_id":"54"}],"abstract":[{"text":"This  paper  presents  an  approach  to  voice  conversion,  whichdoes neither require parallel data nor speaker or phone labels fortraining.  It can convert between speakers which are not in thetraining set by employing the previously proposed concept of afactorized hierarchical variational autoencoder. Here, linguisticand speaker induced variations are separated upon the notionthat content induced variations change at a much shorter timescale, i.e., at the segment level, than speaker induced variations,which vary at the longer utterance level. In this contribution wepropose to employ convolutional instead of recurrent networklayers  in  the  encoder  and  decoder  blocks,  which  is  shown  toachieve better phone recognition accuracy on the latent segmentvariables at frame-level due to their better temporal resolution.For voice conversion the mean of the utterance variables is re-placed with the respective estimated mean of the target speaker.The resulting log-mel spectra of the decoder output are used aslocal conditions of a WaveNet which is utilized for synthesis ofthe speech waveforms.  Experiments show both good disentan-glement properties of the latent space variables, and good voiceconversion performance.","lang":"eng"}],"status":"public","type":"conference","publication":"Proc. 10th ISCA Speech Synthesis Workshop"}]