[{"page":"1185-1197","intvolume":"        32","citation":{"chicago":"Boeddeker, Christoph, Aswin Shanmugam Subramanian, Gordon Wichern, Reinhold Haeb-Umbach, and Jonathan Le Roux. “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i> 32 (2024): 1185–97. <a href=\"https://doi.org/10.1109/taslp.2024.3350887\">https://doi.org/10.1109/taslp.2024.3350887</a>.","ieee":"C. Boeddeker, A. S. Subramanian, G. Wichern, R. Haeb-Umbach, and J. Le Roux, “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings,” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, vol. 32, pp. 1185–1197, 2024, doi: <a href=\"https://doi.org/10.1109/taslp.2024.3350887\">10.1109/taslp.2024.3350887</a>.","ama":"Boeddeker C, Subramanian AS, Wichern G, Haeb-Umbach R, Le Roux J. TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>. 2024;32:1185-1197. doi:<a href=\"https://doi.org/10.1109/taslp.2024.3350887\">10.1109/taslp.2024.3350887</a>","apa":"Boeddeker, C., Subramanian, A. S., Wichern, G., Haeb-Umbach, R., &#38; Le Roux, J. (2024). TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, <i>32</i>, 1185–1197. <a href=\"https://doi.org/10.1109/taslp.2024.3350887\">https://doi.org/10.1109/taslp.2024.3350887</a>","bibtex":"@article{Boeddeker_Subramanian_Wichern_Haeb-Umbach_Le Roux_2024, title={TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings}, volume={32}, DOI={<a href=\"https://doi.org/10.1109/taslp.2024.3350887\">10.1109/taslp.2024.3350887</a>}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Boeddeker, Christoph and Subramanian, Aswin Shanmugam and Wichern, Gordon and Haeb-Umbach, Reinhold and Le Roux, Jonathan}, year={2024}, pages={1185–1197} }","mla":"Boeddeker, Christoph, et al. “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, vol. 32, Institute of Electrical and Electronics Engineers (IEEE), 2024, pp. 1185–97, doi:<a href=\"https://doi.org/10.1109/taslp.2024.3350887\">10.1109/taslp.2024.3350887</a>.","short":"C. Boeddeker, A.S. Subramanian, G. Wichern, R. Haeb-Umbach, J. Le Roux, IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024) 1185–1197."},"has_accepted_license":"1","publication_identifier":{"issn":["2329-9290","2329-9304"]},"publication_status":"published","doi":"10.1109/taslp.2024.3350887","main_file_link":[{"url":"https://arxiv.org/abs/2303.03849","open_access":"1"}],"oa":"1","date_updated":"2025-04-16T10:21:45Z","volume":32,"author":[{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Aswin Shanmugam","last_name":"Subramanian","full_name":"Subramanian, Aswin Shanmugam"},{"first_name":"Gordon","full_name":"Wichern, Gordon","last_name":"Wichern"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"},{"first_name":"Jonathan","last_name":"Le Roux","full_name":"Le Roux, Jonathan"}],"status":"public","type":"journal_article","file_date_updated":"2025-04-16T10:21:45Z","_id":"52958","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"}],"department":[{"_id":"54"}],"user_id":"40767","year":"2024","title":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","date_created":"2024-03-26T16:11:54Z","file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2025-04-16T10:21:45Z","creator":"cbj","date_created":"2025-04-16T10:14:47Z","file_size":3432879,"file_name":"main.pdf","file_id":"59602","access_level":"open_access"},{"access_level":"open_access","file_id":"59603","file_name":"slides.pdf","file_size":2838635,"creator":"cbj","date_created":"2025-04-16T10:15:08Z","date_updated":"2025-04-16T10:21:45Z","relation":"main_file","content_type":"application/pdf"},{"relation":"main_file","content_type":"application/pdf","file_id":"59604","file_name":"poster.pdf","access_level":"open_access","file_size":2038741,"date_created":"2025-04-16T10:15:22Z","creator":"cbj","date_updated":"2025-04-16T10:21:45Z"}],"publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","keyword":["Electrical and Electronic Engineering","Acoustics and Ultrasonics","Computer Science (miscellaneous)","Computational Mathematics"],"ddc":["000"],"language":[{"iso":"eng"}]},{"doi":"10.1109/icasspw62465.2024.10625894","title":"Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization","date_created":"2024-09-04T07:26:02Z","author":[{"last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo"},{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"last_name":"Delcroix","full_name":"Delcroix, Marc","first_name":"Marc"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2025-02-12T09:20:07Z","oa":"1","publisher":"IEEE","citation":{"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} }","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>.","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.","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>","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>.","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>"},"year":"2024","publication_status":"published","has_accepted_license":"1","language":[{"iso":"eng"}],"file_date_updated":"2024-09-04T07:34:30Z","ddc":["000"],"user_id":"40767","department":[{"_id":"54"}],"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"}],"_id":"56004","file":[{"date_created":"2024-09-04T07:34:30Z","creator":"tvn","date_updated":"2024-09-04T07:34:30Z","file_id":"56005","access_level":"open_access","file_name":"main.pdf","file_size":150432,"content_type":"application/pdf","relation":"main_file"}],"status":"public","type":"conference","publication":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"},{"publication_status":"published","citation":{"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>.","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>.","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>","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.","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>"},"year":"2024","author":[{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"first_name":"Tobias","last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_created":"2024-09-30T08:04:47Z","publisher":"ISCA","oa":"1","date_updated":"2025-02-12T09:18:36Z","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/interspeech_2024/boeddeker24_interspeech.pdf"}],"doi":"10.21437/interspeech.2024-1286","title":"Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment","type":"conference","publication":"Interspeech 2024","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":"56272","language":[{"iso":"eng"}]},{"year":"2024","citation":{"apa":"Vieting, P., Berger, S., von Neumann, T., Boeddeker, C., Schlüter, R., &#38; Haeb-Umbach, R. (2024). Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription. <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>.","short":"P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: 2024 IEEE Spoken Language Technology Workshop (SLT), 2024.","bibtex":"@inproceedings{Vieting_Berger_von Neumann_Boeddeker_Schlüter_Haeb-Umbach_2024, title={Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription}, booktitle={2024 IEEE Spoken Language Technology Workshop (SLT)}, author={Vieting, Peter and Berger, Simon and von Neumann, Thilo and Boeddeker, Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2024} }","mla":"Vieting, Peter, et al. “Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription.” <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>, 2024.","ama":"Vieting P, Berger S, von Neumann T, Boeddeker C, Schlüter R, Haeb-Umbach R. Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription. In: <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>. ; 2024.","ieee":"P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach, “Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription,” 2024.","chicago":"Vieting, Peter, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf Schlüter, and Reinhold Haeb-Umbach. “Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription.” In <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>, 2024."},"date_updated":"2025-02-12T09:20:59Z","oa":"1","date_created":"2024-12-09T11:46:18Z","author":[{"first_name":"Peter","full_name":"Vieting, Peter","last_name":"Vieting"},{"full_name":"Berger, Simon","last_name":"Berger","first_name":"Simon"},{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"last_name":"Schlüter","full_name":"Schlüter, Ralf","first_name":"Ralf"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"title":"Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription","main_file_link":[{"url":"https://www-i6.informatik.rwth-aachen.de/publications/download/1259/VietingPeterBergerSimonNeumannThilovonBoeddekerChristophSchl%FCterRalfHaeb-UmbachReinhold--CombiningTF-GridNetMixtureEncoderforContinuousSpeechSeparationforMeetingTranscription--2024.pdf","open_access":"1"}],"publication":"2024 IEEE Spoken Language Technology Workshop (SLT)","type":"conference","status":"public","_id":"57659","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"}],"department":[{"_id":"54"}],"user_id":"40767","language":[{"iso":"eng"}]},{"date_created":"2024-11-14T09:32:38Z","title":"Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models","year":"2024","language":[{"iso":"eng"}],"keyword":["diarization","source separation","mixture model","meeting"],"ddc":["000"],"publication":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","file":[{"date_updated":"2025-08-14T08:11:57Z","date_created":"2025-08-14T08:11:57Z","creator":"cord","file_size":259907,"access_level":"closed","file_name":"main.pdf","file_id":"60930","content_type":"application/pdf","success":1,"relation":"main_file"}],"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."}],"author":[{"full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr","first_name":"Tobias"},{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"date_updated":"2025-08-14T08:12:22Z","oa":"1","doi":"10.1109/ICASSP49660.2025.10888445","conference":{"name":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India"},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/pdf/2410.21455"}],"has_accepted_license":"1","citation":{"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>.","short":"T. Cord-Landwehr, C. Boeddeker, R. Haeb-Umbach, in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.","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>","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>","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>.","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>."},"department":[{"_id":"54"}],"user_id":"44393","_id":"57085","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"file_date_updated":"2025-08-14T08:11:57Z","type":"conference","status":"public"},{"conference":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","location":"Seoul"},"doi":"10.1109/icassp48485.2024.10445911","author":[{"first_name":"Tobias","id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"first_name":"Cătălin","last_name":"Zorilă","full_name":"Zorilă, Cătălin"},{"first_name":"Rama","full_name":"Doddipatla, Rama","last_name":"Doddipatla"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"date_updated":"2025-08-14T08:11:07Z","citation":{"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>","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.","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>.","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>.","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","file_date_updated":"2025-08-14T08:09:52Z","department":[{"_id":"54"}],"user_id":"44393","_id":"53659","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"status":"public","type":"conference","title":"Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios","date_created":"2024-04-25T12:57:22Z","publisher":"IEEE","year":"2024","language":[{"iso":"eng"}],"ddc":["000"],"file":[{"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","relation":"main_file","success":1,"content_type":"application/pdf"}],"publication":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"file_date_updated":"2023-10-19T07:41:56Z","_id":"48281","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"448568305","name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"department":[{"_id":"54"}],"user_id":"40767","status":"public","type":"conference","doi":"10.1109/icassp49357.2023.10094784","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10094784"}],"date_updated":"2025-02-12T09:16:34Z","oa":"1","author":[{"first_name":"Thilo","full_name":"von Neumann, Thilo","id":"49870","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"last_name":"Kinoshita","full_name":"Kinoshita, Keisuke","first_name":"Keisuke"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"citation":{"apa":"von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., &#38; Haeb-Umbach, R. (2023). On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">https://doi.org/10.1109/icassp49357.2023.10094784</a>","mla":"von Neumann, Thilo, et al. “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems.” <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/icassp49357.2023.10094784\">10.1109/icassp49357.2023.10094784</a>.","short":"T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, R. Haeb-Umbach, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023.","bibtex":"@inproceedings{von Neumann_Boeddeker_Kinoshita_Delcroix_Haeb-Umbach_2023, title={On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems}, DOI={<a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">10.1109/icassp49357.2023.10094784</a>}, booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={von Neumann, Thilo and Boeddeker, Christoph and Kinoshita, Keisuke and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2023} }","ama":"von Neumann T, Boeddeker C, Kinoshita K, Delcroix M, Haeb-Umbach R. On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. 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/icassp49357.2023.10094784\">10.1109/icassp49357.2023.10094784</a>","chicago":"Neumann, Thilo von, Christoph Boeddeker, Keisuke Kinoshita, Marc Delcroix, and Reinhold Haeb-Umbach. “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems.” 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/icassp49357.2023.10094784\">https://doi.org/10.1109/icassp49357.2023.10094784</a>.","ieee":"T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, and R. Haeb-Umbach, “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems,” 2023, doi: <a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">10.1109/icassp49357.2023.10094784</a>."},"has_accepted_license":"1","publication_status":"published","related_material":{"link":[{"url":"https://github.com/fgnt/meeteval","relation":"software"}]},"keyword":["Word Error Rate","Meeting Recognition","Levenshtein Distance"],"ddc":["000"],"language":[{"iso":"eng"}],"abstract":[{"text":"\tWe propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple output word sequences (MIMO).\r\n\tSuch ASR systems are typically required, e.g., for meeting transcription.\r\n\tWe provide an efficient implementation based on a dynamic programming search in a multi-dimensional Levenshtein distance tensor under the constraint that a reference utterance must be matched consistently with one hypothesis output. \r\n\tThis also results in an efficient implementation of the ORC WER which previously suffered from exponential complexity.\r\n\tWe give an overview of commonly used WER definitions for multi-speaker scenarios and show that they are specializations of the above MIMO WER tuned to particular application scenarios. \r\n\tWe conclude with a  discussion of the pros and cons of the various WER definitions and a recommendation when to use which.","lang":"eng"}],"file":[{"date_created":"2023-10-19T07:39:57Z","creator":"tvn","date_updated":"2023-10-19T07:41:56Z","file_name":"ICASSP_2023_Meeting_Evaluation.pdf","file_id":"48282","access_level":"open_access","file_size":204994,"content_type":"application/pdf","relation":"main_file"}],"publication":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","title":"On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems","publisher":"IEEE","date_created":"2023-10-19T07:38:31Z","year":"2023","quality_controlled":"1"},{"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2307.11394"}],"conference":{"location":"Dublin","name":"CHiME 2023 Workshop on Speech Processing in Everyday Environments"},"author":[{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","full_name":"von Neumann, Thilo","id":"49870","first_name":"Thilo"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-02-12T09:12:05Z","citation":{"apa":"von Neumann, T., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2023). MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>. CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin.","bibtex":"@inproceedings{von Neumann_Boeddeker_Delcroix_Haeb-Umbach_2023, title={MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems}, booktitle={Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments}, author={von Neumann, Thilo and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2023} }","mla":"von Neumann, Thilo, et al. “MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems.” <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>, 2023.","short":"T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.","chicago":"Neumann, Thilo von, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach. “MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems.” In <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>, 2023.","ieee":"T. von Neumann, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems,” presented at the CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin, 2023.","ama":"von Neumann T, Boeddeker C, Delcroix M, Haeb-Umbach R. MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. In: <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>. ; 2023."},"related_material":{"link":[{"url":"https://github.com/fgnt/meeteval","relation":"software"}]},"has_accepted_license":"1","file_date_updated":"2023-10-19T07:19:59Z","user_id":"40767","department":[{"_id":"54"}],"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":"48275","status":"public","type":"conference","title":"MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems","date_created":"2023-10-19T07:24:51Z","year":"2023","quality_controlled":"1","language":[{"iso":"eng"}],"ddc":["000"],"keyword":["Speech Recognition","Word Error Rate","Meeting Transcription"],"file":[{"file_size":263744,"access_level":"open_access","file_id":"48276","file_name":"Chime_7__MeetEval.pdf","date_updated":"2023-10-19T07:19:59Z","creator":"tvn","date_created":"2023-10-19T07:19:59Z","relation":"main_file","content_type":"application/pdf"}],"abstract":[{"text":"MeetEval is an open-source toolkit to evaluate  all kinds of meeting transcription systems.\r\nIt provides a unified interface for the computation of commonly used Word Error Rates (WERs), specifically cpWER, ORC WER and MIMO WER along other WER definitions.\r\nWe extend the cpWER computation by a temporal constraint to ensure that only words are identified as correct when the temporal alignment is plausible.\r\nThis leads to a better quality of the matching of the hypothesis string to the reference string that more closely resembles the actual transcription quality, and a system is penalized if it provides poor time annotations.\r\nSince word-level timing information is often not available, we present a way to approximate exact word-level timings from segment-level timings (e.g., a sentence) and show that the approximation leads to a similar WER as a matching with exact word-level annotations.\r\nAt the same time, the time constraint leads to a speedup of the matching algorithm, which outweighs the additional overhead caused by processing the time stamps.","lang":"eng"}],"publication":"Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments"},{"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"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"department":[{"_id":"54"}],"user_id":"40767","status":"public","type":"conference","doi":"10.1109/icassp49357.2023.10095370","conference":{"location":"Rhodes","name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},"oa":"1","date_updated":"2025-02-12T09:14:45Z","author":[{"first_name":"Tobias","last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"full_name":"Zorilă, Cătălin","last_name":"Zorilă","first_name":"Cătălin"},{"first_name":"Rama","full_name":"Doddipatla, Rama","last_name":"Doddipatla"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"citation":{"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>","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.","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>.","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>.","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>"},"has_accepted_license":"1","publication_status":"published","ddc":["000"],"language":[{"iso":"eng"}],"file":[{"relation":"main_file","content_type":"application/pdf","access_level":"open_access","file_name":"teacher_student_embeddings.pdf","file_id":"48932","file_size":246306,"date_created":"2023-11-15T14:56:18Z","creator":"cord","date_updated":"2023-11-15T14:56:18Z"}],"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"},{"citation":{"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.","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>.","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} }","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>."},"year":"2023","publication_status":"published","has_accepted_license":"1","doi":"10.21437/interspeech.2023-1379","title":"A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures","author":[{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"first_name":"Cătălin","last_name":"Zorilă","full_name":"Zorilă, Cătălin"},{"first_name":"Rama","last_name":"Doddipatla","full_name":"Doddipatla, Rama"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_created":"2023-09-19T14:34:37Z","oa":"1","date_updated":"2025-02-12T09:15:28Z","publisher":"ISCA","file":[{"file_size":303203,"access_level":"open_access","file_name":"multispeaker_embeddings.pdf","file_id":"48933","date_updated":"2023-11-15T15:00:02Z","creator":"cord","date_created":"2023-11-15T15:00:02Z","relation":"main_file","content_type":"application/pdf"}],"status":"public","type":"conference","publication":"INTERSPEECH 2023","language":[{"iso":"eng"}],"file_date_updated":"2023-11-15T15:00:02Z","ddc":["000"],"user_id":"40767","department":[{"_id":"54"}],"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"}],"_id":"47129"},{"publication_status":"published","year":"2023","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>","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>","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.","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>.","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} }"},"publisher":"ISCA","oa":"1","date_updated":"2025-02-12T09:16:13Z","author":[{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_created":"2024-05-23T15:16:15Z","title":"Multi-stage diarization refinement for the CHiME-7 DASR scenario","doi":"10.21437/chime.2023-10","main_file_link":[{"url":"https://www.isca-archive.org/chime_2023/boeddeker23_chime.pdf","open_access":"1"}],"publication":"7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)","type":"conference","status":"public","_id":"54439","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"department":[{"_id":"54"}],"user_id":"40767","language":[{"iso":"eng"}]},{"type":"conference","publication":"INTERSPEECH 2023","status":"public","project":[{"grant_number":"448568305","name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"_id":"48390","user_id":"40767","department":[{"_id":"54"}],"language":[{"iso":"eng"}],"publication_status":"published","year":"2023","citation":{"ama":"Berger S, Vieting P, Boeddeker C, Schlüter R, Haeb-Umbach R. Mixture Encoder for Joint Speech Separation and Recognition. In: <i>INTERSPEECH 2023</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>","chicago":"Berger, Simon, Peter Vieting, Christoph Boeddeker, Ralf Schlüter, and Reinhold Haeb-Umbach. “Mixture Encoder for Joint Speech Separation and Recognition.” In <i>INTERSPEECH 2023</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/interspeech.2023-1815\">https://doi.org/10.21437/interspeech.2023-1815</a>.","ieee":"S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach, “Mixture Encoder for Joint Speech Separation and Recognition,” 2023, doi: <a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>.","apa":"Berger, S., Vieting, P., Boeddeker, C., Schlüter, R., &#38; Haeb-Umbach, R. (2023). Mixture Encoder for Joint Speech Separation and Recognition. <i>INTERSPEECH 2023</i>. <a href=\"https://doi.org/10.21437/interspeech.2023-1815\">https://doi.org/10.21437/interspeech.2023-1815</a>","mla":"Berger, Simon, et al. “Mixture Encoder for Joint Speech Separation and Recognition.” <i>INTERSPEECH 2023</i>, ISCA, 2023, doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>.","short":"S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.","bibtex":"@inproceedings{Berger_Vieting_Boeddeker_Schlüter_Haeb-Umbach_2023, title={Mixture Encoder for Joint Speech Separation and Recognition}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Berger, Simon and Vieting, Peter and Boeddeker, Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2023} }"},"oa":"1","date_updated":"2025-02-12T09:11:30Z","publisher":"ISCA","author":[{"full_name":"Berger, Simon","last_name":"Berger","first_name":"Simon"},{"first_name":"Peter","last_name":"Vieting","full_name":"Vieting, Peter"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"last_name":"Schlüter","full_name":"Schlüter, Ralf","first_name":"Ralf"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"date_created":"2023-10-23T15:06:39Z","title":"Mixture Encoder for Joint Speech Separation and Recognition","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/interspeech_2023/berger23_interspeech.pdf"}],"doi":"10.21437/interspeech.2023-1815"},{"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."}],"file":[{"creator":"cord","date_created":"2023-11-15T14:52:16Z","date_updated":"2023-11-15T14:52:16Z","access_level":"open_access","file_id":"48930","file_name":"monaural_source_separation.pdf","file_size":212890,"content_type":"application/pdf","relation":"main_file"}],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","ddc":["000"],"language":[{"iso":"eng"}],"external_id":{"arxiv":["2111.07578"]},"year":"2022","title":"Monaural source separation: From anechoic to reverberant environments","publisher":"IEEE","date_created":"2022-10-20T14:07:28Z","status":"public","type":"conference","file_date_updated":"2023-11-15T14:52:16Z","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"}],"_id":"33848","user_id":"40767","department":[{"_id":"54"}],"place":"Bamberg","citation":{"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.","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.","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).","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.","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."},"has_accepted_license":"1","conference":{"name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"date_updated":"2025-02-12T09:05:25Z","oa":"1","author":[{"first_name":"Tobias","id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr"},{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"last_name":"Zorila","full_name":"Zorila, Catalin","first_name":"Catalin"},{"first_name":"Rama","last_name":"Doddipatla","full_name":"Doddipatla, Rama"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}]},{"file":[{"content_type":"application/pdf","relation":"main_file","creator":"tvn","date_created":"2022-10-20T05:33:10Z","date_updated":"2022-10-20T05:33:10Z","file_id":"33820","access_level":"open_access","file_name":"main.pdf","file_size":228069},{"file_id":"33821","file_name":"poster.pdf","access_level":"open_access","file_size":229166,"date_created":"2022-10-20T05:35:32Z","creator":"tvn","date_updated":"2022-10-20T05:35:32Z","relation":"poster","content_type":"application/pdf"}],"publication":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","language":[{"iso":"eng"}],"ddc":["000"],"year":"2022","quality_controlled":"1","title":"SA-SDR: A Novel Loss Function for Separation of Meeting Style Data","date_created":"2022-10-20T05:29:12Z","publisher":"IEEE","status":"public","type":"conference","file_date_updated":"2022-10-20T05:35:32Z","user_id":"40767","department":[{"_id":"54"}],"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"}],"_id":"33819","citation":{"ama":"von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. 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/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>","chicago":"Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” 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/icassp43922.2022.9746757\">https://doi.org/10.1109/icassp43922.2022.9746757</a>.","ieee":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data,” 2022, doi: <a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>.","apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2022). SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">https://doi.org/10.1109/icassp43922.2022.9746757</a>","bibtex":"@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2022, title={SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}, DOI={<a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022.","mla":"von Neumann, Thilo, et al. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” <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/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>."},"related_material":{"link":[{"relation":"supplementary_material","url":"https://github.com/fgnt/graph_pit"}]},"publication_status":"published","has_accepted_license":"1","doi":"10.1109/icassp43922.2022.9746757","author":[{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo"},{"last_name":"Kinoshita","full_name":"Kinoshita, Keisuke","first_name":"Keisuke"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"first_name":"Marc","full_name":"Delcroix, Marc","last_name":"Delcroix"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2025-02-12T09:08:14Z","oa":"1"},{"publisher":"arXiv","date_updated":"2025-02-12T09:03:42Z","oa":"1","author":[{"last_name":"Gburrek","id":"44006","full_name":"Gburrek, Tobias","first_name":"Tobias"},{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Joerg","last_name":"Schmalenstroeer","id":"460","full_name":"Schmalenstroeer, Joerg"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","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","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."},"_id":"33816","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"448568305","name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"department":[{"_id":"54"}],"user_id":"40767","ddc":["004"],"file_date_updated":"2023-11-17T06:42:04Z","language":[{"iso":"eng"}],"type":"misc","status":"public","file":[{"date_updated":"2023-11-17T06:42:04Z","date_created":"2023-11-17T06:42:04Z","creator":"tgburrek","file_size":199006,"file_name":"meeting_transcription_22.pdf","access_level":"open_access","file_id":"48992","content_type":"application/pdf","relation":"main_file"}]},{"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>","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} }","short":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: Interspeech 2022, ISCA, 2022.","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>.","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>","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>.","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>."},"year":"2022","publication_status":"published","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/interspeech_2022/boeddeker22_interspeech.pdf"}],"doi":"10.21437/interspeech.2022-10929","title":"An Initialization Scheme for Meeting Separation with Spatial Mixture Models","date_created":"2022-10-28T10:53:56Z","author":[{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"oa":"1","date_updated":"2025-02-12T09:06:56Z","publisher":"ISCA","status":"public","type":"conference","publication":"Interspeech 2022","language":[{"iso":"eng"}],"user_id":"40767","department":[{"_id":"54"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"_id":"33954"}]