[{"external_id":{"arxiv":["2506.16228"]},"ddc":["000"],"language":[{"iso":"eng"}],"publication":"Proceedings of INTERSPEECH","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"}],"file":[{"relation":"main_file","content_type":"application/pdf","file_id":"61085","file_name":"main.pdf","access_level":"open_access","file_size":921918,"date_created":"2025-08-29T09:43:32Z","creator":"cord","date_updated":"2025-08-29T09:43:32Z"}],"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","_id":"61079","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"54"}],"user_id":"44393","file_date_updated":"2025-08-29T09:43:32Z","type":"conference","status":"public","oa":"1","date_updated":"2025-11-10T09:06:47Z","author":[{"first_name":"Tobias","last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias"},{"full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek","first_name":"Tobias"},{"first_name":"Marc","id":"70272","full_name":"Deegen, Marc","last_name":"Deegen"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"doi":"10.21437/Interspeech.2025-1663","conference":{"location":"Rotterdam","name":"Interspeech 2025"},"has_accepted_license":"1","citation":{"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} }","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>","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>"}},{"publication_identifier":{"isbn":["978-3-8007-6617-8"]},"citation":{"ama":"Meise AT, Cord-Landwehr T, Haeb-Umbach R. On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation. In: <i> ITG Conference on Speech Communication</i>. ; 2025.","chicago":"Meise, Adrian Tobias, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach. “On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation.” In <i> ITG Conference on Speech Communication</i>, 2025.","ieee":"A. T. Meise, T. Cord-Landwehr, and R. Haeb-Umbach, “On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation,” presented at the ITG Conference on Speech Communication, Berlin, 2025.","apa":"Meise, A. T., Cord-Landwehr, T., &#38; Haeb-Umbach, R. (2025). On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation. <i> ITG Conference on Speech Communication</i>. ITG Conference on Speech Communication, Berlin.","bibtex":"@inproceedings{Meise_Cord-Landwehr_Haeb-Umbach_2025, title={On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation}, booktitle={ ITG Conference on Speech Communication}, author={Meise, Adrian Tobias and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2025} }","mla":"Meise, Adrian Tobias, et al. “On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation.” <i> ITG Conference on Speech Communication</i>, 2025.","short":"A.T. Meise, T. Cord-Landwehr, R. Haeb-Umbach, in:  ITG Conference on Speech Communication, 2025."},"year":"2025","date_created":"2025-11-13T07:21:51Z","author":[{"first_name":"Adrian Tobias","last_name":"Meise","id":"79268","full_name":"Meise, Adrian Tobias"},{"first_name":"Tobias","last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_updated":"2026-01-05T09:05:14Z","conference":{"name":"ITG Conference on Speech Communication","location":"Berlin"},"title":"On the Application of Diffusion Models for Simultaneous Denoising and Dereverberation","publication":" ITG Conference on Speech Communication","type":"conference","status":"public","department":[{"_id":"54"}],"user_id":"44393","_id":"62174","language":[{"iso":"eng"}]},{"title":"Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization","doi":"10.1109/icasspw62465.2024.10625894","date_updated":"2025-02-12T09:20:07Z","publisher":"IEEE","oa":"1","author":[{"full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"first_name":"Marc","full_name":"Delcroix, Marc","last_name":"Delcroix"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_created":"2024-09-04T07:26:02Z","year":"2024","citation":{"ama":"von Neumann T, Boeddeker C, Cord-Landwehr T, Delcroix M, Haeb-Umbach R. Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. In: <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>. IEEE; 2024. doi:<a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>","chicago":"Neumann, Thilo von, Christoph Boeddeker, Tobias Cord-Landwehr, Marc Delcroix, and Reinhold Haeb-Umbach. “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization.” In <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>. IEEE, 2024. <a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">https://doi.org/10.1109/icasspw62465.2024.10625894</a>.","ieee":"T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, and R. Haeb-Umbach, “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization,” 2024, doi: <a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>.","short":"T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, R. Haeb-Umbach, in: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2024.","mla":"von Neumann, Thilo, et al. “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization.” <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>, IEEE, 2024, doi:<a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>.","bibtex":"@inproceedings{von Neumann_Boeddeker_Cord-Landwehr_Delcroix_Haeb-Umbach_2024, title={Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization}, DOI={<a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>}, booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, publisher={IEEE}, author={von Neumann, Thilo and Boeddeker, Christoph and Cord-Landwehr, Tobias and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2024} }","apa":"von Neumann, T., Boeddeker, C., Cord-Landwehr, T., Delcroix, M., &#38; Haeb-Umbach, R. (2024). Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>. <a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">https://doi.org/10.1109/icasspw62465.2024.10625894</a>"},"has_accepted_license":"1","publication_status":"published","ddc":["000"],"language":[{"iso":"eng"}],"file_date_updated":"2024-09-04T07:34:30Z","_id":"56004","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"department":[{"_id":"54"}],"user_id":"40767","status":"public","file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2024-09-04T07:34:30Z","creator":"tvn","date_created":"2024-09-04T07:34:30Z","file_size":150432,"access_level":"open_access","file_id":"56005","file_name":"main.pdf"}],"publication":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","type":"conference"},{"year":"2024","citation":{"apa":"Boeddeker, C., Cord-Landwehr, T., &#38; Haeb-Umbach, R. (2024). Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment. <i>Interspeech 2024</i>. <a href=\"https://doi.org/10.21437/interspeech.2024-1286\">https://doi.org/10.21437/interspeech.2024-1286</a>","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_Haeb-Umbach_2024, title={Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2024-1286\">10.21437/interspeech.2024-1286</a>}, booktitle={Interspeech 2024}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2024} }","mla":"Boeddeker, Christoph, et al. “Once More Diarization: Improving Meeting Transcription Systems through Segment-Level Speaker Reassignment.” <i>Interspeech 2024</i>, ISCA, 2024, doi:<a href=\"https://doi.org/10.21437/interspeech.2024-1286\">10.21437/interspeech.2024-1286</a>.","short":"C. Boeddeker, T. Cord-Landwehr, R. Haeb-Umbach, in: Interspeech 2024, ISCA, 2024.","ama":"Boeddeker C, Cord-Landwehr T, Haeb-Umbach R. Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment. In: <i>Interspeech 2024</i>. ISCA; 2024. doi:<a href=\"https://doi.org/10.21437/interspeech.2024-1286\">10.21437/interspeech.2024-1286</a>","ieee":"C. Boeddeker, T. Cord-Landwehr, and R. Haeb-Umbach, “Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment,” 2024, doi: <a href=\"https://doi.org/10.21437/interspeech.2024-1286\">10.21437/interspeech.2024-1286</a>.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach. “Once More Diarization: Improving Meeting Transcription Systems through Segment-Level Speaker Reassignment.” In <i>Interspeech 2024</i>. ISCA, 2024. <a href=\"https://doi.org/10.21437/interspeech.2024-1286\">https://doi.org/10.21437/interspeech.2024-1286</a>."},"publication_status":"published","title":"Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/interspeech_2024/boeddeker24_interspeech.pdf"}],"doi":"10.21437/interspeech.2024-1286","oa":"1","publisher":"ISCA","date_updated":"2025-02-12T09:18:36Z","date_created":"2024-09-30T08:04:47Z","author":[{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"status":"public","type":"conference","publication":"Interspeech 2024","language":[{"iso":"eng"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"_id":"56272","user_id":"40767","department":[{"_id":"54"}]},{"citation":{"chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models.” In <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2024. <a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">https://doi.org/10.1109/ICASSP49660.2025.10888445</a>.","ieee":"T. Cord-Landwehr, C. Boeddeker, and R. Haeb-Umbach, “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models,” presented at the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2024, doi: <a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>.","ama":"Cord-Landwehr T, Boeddeker C, Haeb-Umbach R. Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models. In: <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2024. doi:<a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>","short":"T. Cord-Landwehr, C. Boeddeker, R. Haeb-Umbach, in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.","mla":"Cord-Landwehr, Tobias, et al. “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models.” <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2024, doi:<a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Haeb-Umbach_2024, title={Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models}, DOI={<a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>}, booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2024} }","apa":"Cord-Landwehr, T., Boeddeker, C., &#38; Haeb-Umbach, R. (2024). Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models. <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India. <a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">https://doi.org/10.1109/ICASSP49660.2025.10888445</a>"},"has_accepted_license":"1","main_file_link":[{"url":"https://arxiv.org/pdf/2410.21455","open_access":"1"}],"doi":"10.1109/ICASSP49660.2025.10888445","conference":{"name":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India"},"oa":"1","date_updated":"2025-08-14T08:12:22Z","author":[{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"status":"public","type":"conference","file_date_updated":"2025-08-14T08:11:57Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"_id":"57085","user_id":"44393","department":[{"_id":"54"}],"year":"2024","title":"Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models","date_created":"2024-11-14T09:32:38Z","abstract":[{"lang":"eng","text":"We propose an approach for simultaneous diarization and separation of meeting data. It consists of a complex Angular Central Gaussian Mixture Model (cACGMM) for speech source separation, and a von-Mises-Fisher Mixture Model (VMFMM) for diarization in a joint statistical framework. Through the integration, both spatial and spectral information are exploited for diarization and separation. We also develop a method for counting the number of active speakers in a segment of a meeting to support block-wise processing. While the total number of speakers in a meeting may be known, it is usually not known on a per-segment level. With the proposed speaker counting, joint diarization and source separation can be done segment-by-segment, and the permutation problem across segments is solved, thus allowing for block-online processing in the future. Experimental results on the LibriCSS meeting corpus show that the integrated approach outperforms a cascaded approach of diarization and speech enhancement in terms of WER, both on a per-segment and on a per-meeting level."}],"file":[{"file_size":259907,"file_id":"60930","file_name":"main.pdf","access_level":"closed","date_updated":"2025-08-14T08:11:57Z","creator":"cord","date_created":"2025-08-14T08:11:57Z","success":1,"relation":"main_file","content_type":"application/pdf"}],"publication":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","ddc":["000"],"keyword":["diarization","source separation","mixture model","meeting"],"language":[{"iso":"eng"}]},{"status":"public","type":"conference","file_date_updated":"2025-08-14T08:09:52Z","department":[{"_id":"54"}],"user_id":"44393","_id":"53659","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"citation":{"mla":"Cord-Landwehr, Tobias, et al. “Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios.” <i>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2024, doi:<a href=\"https://doi.org/10.1109/icassp48485.2024.10445911\">10.1109/icassp48485.2024.10445911</a>.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2024, title={Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios}, DOI={<a href=\"https://doi.org/10.1109/icassp48485.2024.10445911\">10.1109/icassp48485.2024.10445911</a>}, booktitle={ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2024} }","short":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach, in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2024.","apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2024). Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios. <i>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul. <a href=\"https://doi.org/10.1109/icassp48485.2024.10445911\">https://doi.org/10.1109/icassp48485.2024.10445911</a>","ieee":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, and R. Haeb-Umbach, “Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios,” presented at the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, 2024, doi: <a href=\"https://doi.org/10.1109/icassp48485.2024.10445911\">10.1109/icassp48485.2024.10445911</a>.","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, and Reinhold Haeb-Umbach. “Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios.” In <i>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2024. <a href=\"https://doi.org/10.1109/icassp48485.2024.10445911\">https://doi.org/10.1109/icassp48485.2024.10445911</a>.","ama":"Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios. In: <i>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2024. doi:<a href=\"https://doi.org/10.1109/icassp48485.2024.10445911\">10.1109/icassp48485.2024.10445911</a>"},"has_accepted_license":"1","publication_status":"published","doi":"10.1109/icassp48485.2024.10445911","conference":{"location":"Seoul","name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},"author":[{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"first_name":"Cătălin","last_name":"Zorilă","full_name":"Zorilă, Cătălin"},{"last_name":"Doddipatla","full_name":"Doddipatla, Rama","first_name":"Rama"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2025-08-14T08:11:07Z","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","file_id":"60929","access_level":"closed","file_name":"main.pdf","file_size":254478,"creator":"cord","date_created":"2025-08-14T08:09:52Z","date_updated":"2025-08-14T08:09:52Z"}],"publication":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","language":[{"iso":"eng"}],"ddc":["000"],"year":"2024","title":"Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios","date_created":"2024-04-25T12:57:22Z","publisher":"IEEE"},{"file_date_updated":"2023-11-15T14:56:18Z","_id":"47128","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"department":[{"_id":"54"}],"user_id":"40767","status":"public","type":"conference","conference":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","location":"Rhodes"},"doi":"10.1109/icassp49357.2023.10095370","oa":"1","date_updated":"2025-02-12T09:14:45Z","author":[{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"first_name":"Cătălin","full_name":"Zorilă, Cătălin","last_name":"Zorilă"},{"first_name":"Rama","last_name":"Doddipatla","full_name":"Doddipatla, Rama"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"citation":{"ama":"Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. In: <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2023. doi:<a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>","ieee":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, and R. Haeb-Umbach, “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization,” presented at the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, 2023, doi: <a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>.","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, and Reinhold Haeb-Umbach. “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.” In <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2023. <a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">https://doi.org/10.1109/icassp49357.2023.10095370</a>.","mla":"Cord-Landwehr, Tobias, et al. “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.” <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2023, doi:<a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization}, DOI={<a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>}, booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2023} }","short":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023.","apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2023). Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes. <a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">https://doi.org/10.1109/icassp49357.2023.10095370</a>"},"has_accepted_license":"1","publication_status":"published","ddc":["000"],"language":[{"iso":"eng"}],"file":[{"file_size":246306,"file_name":"teacher_student_embeddings.pdf","file_id":"48932","access_level":"open_access","date_updated":"2023-11-15T14:56:18Z","creator":"cord","date_created":"2023-11-15T14:56:18Z","relation":"main_file","content_type":"application/pdf"}],"publication":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","title":"Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization","publisher":"IEEE","date_created":"2023-09-19T14:01:20Z","year":"2023"},{"title":"A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures","doi":"10.21437/interspeech.2023-1379","oa":"1","date_updated":"2025-02-12T09:15:28Z","publisher":"ISCA","author":[{"id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr","first_name":"Tobias"},{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Cătălin","last_name":"Zorilă","full_name":"Zorilă, Cătălin"},{"first_name":"Rama","full_name":"Doddipatla, Rama","last_name":"Doddipatla"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"date_created":"2023-09-19T14:34:37Z","year":"2023","citation":{"ama":"Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. In: <i>INTERSPEECH 2023</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, and Reinhold Haeb-Umbach. “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures.” In <i>INTERSPEECH 2023</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/interspeech.2023-1379\">https://doi.org/10.21437/interspeech.2023-1379</a>.","ieee":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, and R. Haeb-Umbach, “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures,” 2023, doi: <a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>.","apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2023). A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. <i>INTERSPEECH 2023</i>. <a href=\"https://doi.org/10.21437/interspeech.2023-1379\">https://doi.org/10.21437/interspeech.2023-1379</a>","short":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2023} }","mla":"Cord-Landwehr, Tobias, et al. “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures.” <i>INTERSPEECH 2023</i>, ISCA, 2023, doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>."},"has_accepted_license":"1","publication_status":"published","ddc":["000"],"file_date_updated":"2023-11-15T15:00:02Z","language":[{"iso":"eng"}],"_id":"47129","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"department":[{"_id":"54"}],"user_id":"40767","status":"public","file":[{"relation":"main_file","content_type":"application/pdf","file_size":303203,"file_name":"multispeaker_embeddings.pdf","access_level":"open_access","file_id":"48933","date_updated":"2023-11-15T15:00:02Z","date_created":"2023-11-15T15:00:02Z","creator":"cord"}],"publication":"INTERSPEECH 2023","type":"conference"},{"department":[{"_id":"54"}],"user_id":"40767","_id":"54439","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"grant_number":"448568305","_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"language":[{"iso":"eng"}],"publication":"7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)","type":"conference","status":"public","date_created":"2024-05-23T15:16:15Z","author":[{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr","first_name":"Tobias"},{"id":"49870","full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","first_name":"Thilo"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"publisher":"ISCA","oa":"1","date_updated":"2025-02-12T09:16:13Z","doi":"10.21437/chime.2023-10","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/chime_2023/boeddeker23_chime.pdf"}],"title":"Multi-stage diarization refinement for the CHiME-7 DASR scenario","publication_status":"published","citation":{"ieee":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “Multi-stage diarization refinement for the CHiME-7 DASR scenario,” 2023, doi: <a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.” In <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/chime.2023-10\">https://doi.org/10.21437/chime.2023-10</a>.","ama":"Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. Multi-stage diarization refinement for the CHiME-7 DASR scenario. In: <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>","mla":"Boeddeker, Christoph, et al. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.” <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>, ISCA, 2023, doi:<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>.","short":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023), ISCA, 2023.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2023, title={Multi-stage diarization refinement for the CHiME-7 DASR scenario}, DOI={<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>}, booktitle={7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2023} }","apa":"Boeddeker, C., Cord-Landwehr, T., von Neumann, T., &#38; Haeb-Umbach, R. (2023). Multi-stage diarization refinement for the CHiME-7 DASR scenario. <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. <a href=\"https://doi.org/10.21437/chime.2023-10\">https://doi.org/10.21437/chime.2023-10</a>"},"year":"2023"},{"external_id":{"arxiv":["2209.11494"]},"language":[{"iso":"eng"}],"ddc":["000"],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","file":[{"date_updated":"2023-11-15T14:54:56Z","creator":"cord","date_created":"2023-11-15T14:54:56Z","file_size":177975,"access_level":"open_access","file_name":"mms_msg_camera_ready.pdf","file_id":"48931","content_type":"application/pdf","relation":"main_file"}],"abstract":[{"text":"The scope of speech enhancement has changed from a monolithic view of single,\r\nindependent tasks, to a joint processing of complex conversational speech\r\nrecordings. Training and evaluation of these single tasks requires synthetic\r\ndata with access to intermediate signals that is as close as possible to the\r\nevaluation scenario. As such data often is not available, many works instead\r\nuse specialized databases for the training of each system component, e.g\r\nWSJ0-mix for source separation. We present a Multi-purpose Multi-Speaker\r\nMixture Signal Generator (MMS-MSG) for generating a variety of speech mixture\r\nsignals based on any speech corpus, ranging from classical anechoic mixtures\r\n(e.g., WSJ0-mix) over reverberant mixtures (e.g., SMS-WSJ) to meeting-style\r\ndata. Its highly modular and flexible structure allows for the simulation of\r\ndiverse environments and dynamic mixing, while simultaneously enabling an easy\r\nextension and modification to generate new scenarios and mixture types. These\r\nmeetings can be used for prototyping, evaluation, or training purposes. We\r\nprovide example evaluation data and baseline results for meetings based on the\r\nWSJ corpus. Further, we demonstrate the usefulness for realistic scenarios by\r\nusing MMS-MSG to provide training data for the LibriCSS database.","lang":"eng"}],"date_created":"2022-10-20T14:02:14Z","title":"MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator","quality_controlled":"1","year":"2022","department":[{"_id":"54"}],"user_id":"44393","_id":"33847","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"file_date_updated":"2023-11-15T14:54:56Z","type":"conference","status":"public","author":[{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"first_name":"Thilo","id":"49870","full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"oa":"1","date_updated":"2023-11-15T14:55:14Z","conference":{"location":"Bamberg","name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"has_accepted_license":"1","citation":{"apa":"Cord-Landwehr, T., von Neumann, T., Boeddeker, C., &#38; Haeb-Umbach, R. (2022). MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg.","bibtex":"@inproceedings{Cord-Landwehr_von Neumann_Boeddeker_Haeb-Umbach_2022, title={MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator}, booktitle={2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}, author={Cord-Landwehr, Tobias and von Neumann, Thilo and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. Cord-Landwehr, T. von Neumann, C. Boeddeker, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.","mla":"Cord-Landwehr, Tobias, et al. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.” <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, 2022.","ieee":"T. Cord-Landwehr, T. von Neumann, C. Boeddeker, and R. Haeb-Umbach, “MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator,” presented at the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg, 2022.","chicago":"Cord-Landwehr, Tobias, Thilo von Neumann, Christoph Boeddeker, and Reinhold Haeb-Umbach. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, 2022.","ama":"Cord-Landwehr T, von Neumann T, Boeddeker C, Haeb-Umbach R. MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. ; 2022."}},{"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","file":[{"relation":"main_file","content_type":"application/pdf","file_size":212890,"file_id":"48930","file_name":"monaural_source_separation.pdf","access_level":"open_access","date_updated":"2023-11-15T14:52:16Z","date_created":"2023-11-15T14:52:16Z","creator":"cord"}],"abstract":[{"lang":"eng","text":"Impressive progress in neural network-based single-channel speech source\r\nseparation has been made in recent years. But those improvements have been\r\nmostly reported on anechoic data, a situation that is hardly met in practice.\r\nTaking the SepFormer as a starting point, which achieves state-of-the-art\r\nperformance on anechoic mixtures, we gradually modify it to optimize its\r\nperformance on reverberant mixtures. Although this leads to a word error rate\r\nimprovement by 7 percentage points compared to the standard SepFormer\r\nimplementation, the system ends up with only marginally better performance than\r\na PIT-BLSTM separation system, that is optimized with rather straightforward\r\nmeans. This is surprising and at the same time sobering, challenging the\r\npractical usefulness of many improvements reported in recent years for monaural\r\nsource separation on nonreverberant data."}],"external_id":{"arxiv":["2111.07578"]},"language":[{"iso":"eng"}],"ddc":["000"],"year":"2022","date_created":"2022-10-20T14:07:28Z","publisher":"IEEE","title":"Monaural source separation: From anechoic to reverberant environments","type":"conference","status":"public","user_id":"40767","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"grant_number":"448568305","name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"_id":"33848","file_date_updated":"2023-11-15T14:52:16Z","has_accepted_license":"1","citation":{"bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_von Neumann_Zorila_Doddipatla_Haeb-Umbach_2022, place={Bamberg}, title={Monaural source separation: From anechoic to reverberant environments}, booktitle={2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Zorila, Catalin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2022} }","mla":"Cord-Landwehr, Tobias, et al. “Monaural Source Separation: From Anechoic to Reverberant Environments.” <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, IEEE, 2022.","short":"T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, Bamberg, 2022.","apa":"Cord-Landwehr, T., Boeddeker, C., von Neumann, T., Zorila, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2022). Monaural source separation: From anechoic to reverberant environments. <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC).","ieee":"T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla, and R. Haeb-Umbach, “Monaural source separation: From anechoic to reverberant environments,” presented at the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, and Reinhold Haeb-Umbach. “Monaural Source Separation: From Anechoic to Reverberant Environments.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. Bamberg: IEEE, 2022.","ama":"Cord-Landwehr T, Boeddeker C, von Neumann T, Zorila C, Doddipatla R, Haeb-Umbach R. Monaural source separation: From anechoic to reverberant environments. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE; 2022."},"place":"Bamberg","author":[{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo"},{"first_name":"Catalin","last_name":"Zorila","full_name":"Zorila, Catalin"},{"last_name":"Doddipatla","full_name":"Doddipatla, Rama","first_name":"Rama"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"oa":"1","date_updated":"2025-02-12T09:05:25Z","conference":{"name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"}},{"type":"misc","file":[{"date_updated":"2023-11-17T06:42:04Z","creator":"tgburrek","date_created":"2023-11-17T06:42:04Z","file_size":199006,"file_name":"meeting_transcription_22.pdf","access_level":"open_access","file_id":"48992","content_type":"application/pdf","relation":"main_file"}],"status":"public","user_id":"40767","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"_id":"33816","language":[{"iso":"eng"}],"file_date_updated":"2023-11-17T06:42:04Z","ddc":["004"],"has_accepted_license":"1","citation":{"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.","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>","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>","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} }","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>.","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."},"year":"2022","date_created":"2022-10-18T11:10:58Z","author":[{"first_name":"Tobias","full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo"},{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer","first_name":"Joerg"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2025-02-12T09:03:42Z","publisher":"arXiv","oa":"1","doi":"10.48550/ARXIV.2205.00944","title":"A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network"},{"language":[{"iso":"eng"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"_id":"33954","user_id":"40767","department":[{"_id":"54"}],"status":"public","type":"conference","publication":"Interspeech 2022","title":"An Initialization Scheme for Meeting Separation with Spatial Mixture Models","main_file_link":[{"url":"https://www.isca-archive.org/interspeech_2022/boeddeker22_interspeech.pdf","open_access":"1"}],"doi":"10.21437/interspeech.2022-10929","date_updated":"2025-02-12T09:06:56Z","oa":"1","publisher":"ISCA","author":[{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"first_name":"Tobias","last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393"},{"first_name":"Thilo","id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"date_created":"2022-10-28T10:53:56Z","year":"2022","citation":{"apa":"Boeddeker, C., Cord-Landwehr, T., von Neumann, T., &#38; Haeb-Umbach, R. (2022). An Initialization Scheme for Meeting Separation with Spatial Mixture Models. <i>Interspeech 2022</i>. <a href=\"https://doi.org/10.21437/interspeech.2022-10929\">https://doi.org/10.21437/interspeech.2022-10929</a>","mla":"Boeddeker, Christoph, et al. “An Initialization Scheme for Meeting Separation with Spatial Mixture Models.” <i>Interspeech 2022</i>, ISCA, 2022, doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>.","short":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: Interspeech 2022, ISCA, 2022.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2022, title={An Initialization Scheme for Meeting Separation with Spatial Mixture Models}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>}, booktitle={Interspeech 2022}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2022} }","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “An Initialization Scheme for Meeting Separation with Spatial Mixture Models.” In <i>Interspeech 2022</i>. ISCA, 2022. <a href=\"https://doi.org/10.21437/interspeech.2022-10929\">https://doi.org/10.21437/interspeech.2022-10929</a>.","ieee":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “An Initialization Scheme for Meeting Separation with Spatial Mixture Models,” 2022, doi: <a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>.","ama":"Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. An Initialization Scheme for Meeting Separation with Spatial Mixture Models. In: <i>Interspeech 2022</i>. ISCA; 2022. doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>"},"publication_status":"published"},{"publication":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","file":[{"date_updated":"2022-01-13T08:19:19Z","creator":"ebbers","date_created":"2022-01-13T07:56:30Z","file_size":236628,"file_id":"29305","file_name":"Template.pdf","access_level":"open_access","content_type":"application/pdf","relation":"main_file"}],"abstract":[{"lang":"eng","text":"In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose adversarial contrastive predictive coding. This new disentanglement method does neither need parallel data nor any supervision. We show that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches. We further demonstrate an increased robustness of the content representation against a train-test mismatch compared to spectral features, when used for phone recognition."}],"language":[{"iso":"eng"}],"ddc":["000"],"quality_controlled":"1","year":"2021","date_created":"2022-01-13T07:55:29Z","title":"Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations","type":"conference","status":"public","department":[{"_id":"54"}],"user_id":"34851","_id":"29304","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"file_date_updated":"2022-01-13T08:19:19Z","has_accepted_license":"1","page":"3860–3864","citation":{"apa":"Ebbers, J., Kuhlmann, M., Cord-Landwehr, T., &#38; Haeb-Umbach, R. (2021). Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations. <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 3860–3864.","mla":"Ebbers, Janek, et al. “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations.” <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2021, pp. 3860–3864.","short":"J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, R. Haeb-Umbach, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 3860–3864.","bibtex":"@inproceedings{Ebbers_Kuhlmann_Cord-Landwehr_Haeb-Umbach_2021, title={Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Ebbers, Janek and Kuhlmann, Michael and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2021}, pages={3860–3864} }","ama":"Ebbers J, Kuhlmann M, Cord-Landwehr T, Haeb-Umbach R. Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations. In: <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2021:3860–3864.","ieee":"J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, and R. Haeb-Umbach, “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations,” in <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2021, pp. 3860–3864.","chicago":"Ebbers, Janek, Michael Kuhlmann, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach. “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations.” In <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 3860–3864, 2021."},"author":[{"id":"34851","full_name":"Ebbers, Janek","last_name":"Ebbers","first_name":"Janek"},{"first_name":"Michael","full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann"},{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"oa":"1","date_updated":"2023-11-22T08:29:42Z"},{"type":"conference","publication":"Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments","file":[{"file_size":115421,"file_name":"template.pdf","access_level":"open_access","file_id":"20702","date_updated":"2020-12-11T12:48:48Z","date_created":"2020-12-11T12:48:48Z","creator":"cbj","relation":"main_file","content_type":"application/pdf"}],"status":"public","user_id":"40767","department":[{"_id":"54"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"20700","file_date_updated":"2020-12-11T12:48:48Z","language":[{"iso":"eng"}],"ddc":["000"],"has_accepted_license":"1","citation":{"ieee":"C. Boeddeker <i>et al.</i>, “Towards a speaker diarization system for the CHiME 2020 dinner party transcription,” in <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>, 2020.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Jens Heitkaemper, Catalin Zorila, Daichi Hayakawa, Mohan Li, Min Liu, Rama Doddipatla, and Reinhold Haeb-Umbach. “Towards a Speaker Diarization System for the CHiME 2020 Dinner Party Transcription.” In <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>, 2020.","ama":"Boeddeker C, Cord-Landwehr T, Heitkaemper J, et al. Towards a speaker diarization system for the CHiME 2020 dinner party transcription. In: <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>. ; 2020.","apa":"Boeddeker, C., Cord-Landwehr, T., Heitkaemper, J., Zorila, C., Hayakawa, D., Li, M., … Haeb-Umbach, R. (2020). Towards a speaker diarization system for the CHiME 2020 dinner party transcription. In <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>.","mla":"Boeddeker, Christoph, et al. “Towards a Speaker Diarization System for the CHiME 2020 Dinner Party Transcription.” <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>, 2020.","short":"C. Boeddeker, T. Cord-Landwehr, J. Heitkaemper, C. Zorila, D. Hayakawa, M. Li, M. Liu, R. Doddipatla, R. Haeb-Umbach, in: Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments, 2020.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_Heitkaemper_Zorila_Hayakawa_Li_Liu_Doddipatla_Haeb-Umbach_2020, title={Towards a speaker diarization system for the CHiME 2020 dinner party transcription}, booktitle={Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and Heitkaemper, Jens and Zorila, Catalin and Hayakawa, Daichi and Li, Mohan and Liu, Min and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2020} }"},"year":"2020","date_created":"2020-12-11T12:49:13Z","author":[{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Jens","full_name":"Heitkaemper, Jens","id":"27643","last_name":"Heitkaemper"},{"first_name":"Catalin","last_name":"Zorila","full_name":"Zorila, Catalin"},{"first_name":"Daichi","last_name":"Hayakawa","full_name":"Hayakawa, Daichi"},{"first_name":"Mohan","last_name":"Li","full_name":"Li, Mohan"},{"full_name":"Liu, Min","last_name":"Liu","first_name":"Min"},{"last_name":"Doddipatla","full_name":"Doddipatla, Rama","first_name":"Rama"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"oa":"1","date_updated":"2022-01-06T06:54:33Z","title":"Towards a speaker diarization system for the CHiME 2020 dinner party transcription"}]