[{"has_accepted_license":"1","citation":{"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>","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>.","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>.","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>","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>.","short":"T. Cord-Landwehr, T. Gburrek, M. Deegen, R. Haeb-Umbach, in: Proceedings of INTERSPEECH, 2025.","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} }"},"author":[{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Tobias","last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006"},{"first_name":"Marc","full_name":"Deegen, Marc","id":"70272","last_name":"Deegen"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2025-11-10T09:06:47Z","oa":"1","doi":"10.21437/Interspeech.2025-1663","conference":{"location":"Rotterdam","name":"Interspeech 2025"},"type":"conference","status":"public","user_id":"44393","department":[{"_id":"54"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"61079","file_date_updated":"2025-08-29T09:43:32Z","year":"2025","date_created":"2025-08-29T09:39:01Z","title":"Spatio-spectral diarization of meetings by combining TDOA-based  segmentation and speaker embedding-based clustering","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,"date_created":"2025-08-29T09:43:32Z","creator":"cord","date_updated":"2025-08-29T09:43:32Z"}],"abstract":[{"lang":"eng","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."}],"external_id":{"arxiv":["2506.16228"]},"language":[{"iso":"eng"}],"ddc":["000"]}]