[{"type":"preprint","publication":"arXiv:2407.16447","abstract":[{"text":"This paper presents the CHiME-8 DASR challenge which carries on from the\r\nprevious edition CHiME-7 DASR (C7DASR) and the past CHiME-6 challenge. It\r\nfocuses on joint multi-channel distant speech recognition (DASR) and\r\ndiarization with one or more, possibly heterogeneous, devices. The main goal is\r\nto spur research towards meeting transcription approaches that can generalize\r\nacross arbitrary number of speakers, diverse settings (formal vs. informal\r\nconversations), meeting duration, wide-variety of acoustic scenarios and\r\ndifferent recording configurations. Novelties with respect to C7DASR include:\r\ni) the addition of NOTSOFAR-1, an additional office/corporate meeting scenario,\r\nii) a manually corrected Mixer 6 development set, iii) a new track in which we\r\nallow the use of large-language models (LLM) iv) a jury award mechanism to\r\nencourage participants to explore also more practical and innovative solutions.\r\nTo lower the entry barrier for participants, we provide a standalone toolkit\r\nfor downloading and preparing such datasets as well as performing text\r\nnormalization and scoring their submissions. Furthermore, this year we also\r\nprovide two baseline systems, one directly inherited from C7DASR and based on\r\nESPnet and another one developed on NeMo and based on NeMo team submission in\r\nlast year C7DASR. Baseline system results suggest that the addition of the\r\nNOTSOFAR-1 scenario significantly increases the task's difficulty due to its\r\nhigh number of speakers and very short duration.","lang":"eng"}],"status":"public","external_id":{"arxiv":["2407.16447"]},"_id":"56273","user_id":"40767","department":[{"_id":"54"}],"language":[{"iso":"eng"}],"year":"2024","citation":{"bibtex":"@article{Cornell_Park_Huang_Boeddeker_Chang_Maciejewski_Wiesner_Garcia_Watanabe_2024, title={The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization}, journal={arXiv:2407.16447}, author={Cornell, Samuele and Park, Taejin and Huang, Steve and Boeddeker, Christoph and Chang, Xuankai and Maciejewski, Matthew and Wiesner, Matthew and Garcia, Paola and Watanabe, Shinji}, year={2024} }","mla":"Cornell, Samuele, et al. “The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization.” ArXiv:2407.16447, 2024.","short":"S. Cornell, T. Park, S. Huang, C. Boeddeker, X. Chang, M. Maciejewski, M. Wiesner, P. Garcia, S. Watanabe, ArXiv:2407.16447 (2024).","apa":"Cornell, S., Park, T., Huang, S., Boeddeker, C., Chang, X., Maciejewski, M., Wiesner, M., Garcia, P., & Watanabe, S. (2024). The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization. In arXiv:2407.16447.","ieee":"S. Cornell et al., “The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization,” arXiv:2407.16447. 2024.","chicago":"Cornell, Samuele, Taejin Park, Steve Huang, Christoph Boeddeker, Xuankai Chang, Matthew Maciejewski, Matthew Wiesner, Paola Garcia, and Shinji Watanabe. “The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization.” ArXiv:2407.16447, 2024.","ama":"Cornell S, Park T, Huang S, et al. The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization. arXiv:240716447. Published online 2024."},"oa":"1","date_updated":"2024-09-30T08:09:40Z","date_created":"2024-09-30T08:08:46Z","author":[{"first_name":"Samuele","last_name":"Cornell","full_name":"Cornell, Samuele"},{"last_name":"Park","full_name":"Park, Taejin","first_name":"Taejin"},{"first_name":"Steve","last_name":"Huang","full_name":"Huang, Steve"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"first_name":"Xuankai","last_name":"Chang","full_name":"Chang, Xuankai"},{"last_name":"Maciejewski","full_name":"Maciejewski, Matthew","first_name":"Matthew"},{"last_name":"Wiesner","full_name":"Wiesner, Matthew","first_name":"Matthew"},{"first_name":"Paola","last_name":"Garcia","full_name":"Garcia, Paola"},{"full_name":"Watanabe, Shinji","last_name":"Watanabe","first_name":"Shinji"}],"title":"The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization","main_file_link":[{"url":"https://arxiv.org/pdf/2407.16447","open_access":"1"}]},{"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":[{"date_updated":"2025-04-16T10:21:45Z","date_created":"2025-04-16T10:14:47Z","creator":"cbj","file_size":3432879,"file_name":"main.pdf","file_id":"59602","access_level":"open_access","content_type":"application/pdf","relation":"main_file"},{"relation":"main_file","content_type":"application/pdf","file_id":"59603","access_level":"open_access","file_name":"slides.pdf","file_size":2838635,"creator":"cbj","date_created":"2025-04-16T10:15:08Z","date_updated":"2025-04-16T10:21:45Z"},{"creator":"cbj","date_created":"2025-04-16T10:15:22Z","date_updated":"2025-04-16T10:21:45Z","file_id":"59604","file_name":"poster.pdf","access_level":"open_access","file_size":2038741,"content_type":"application/pdf","relation":"main_file"}],"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"}],"page":"1185-1197","intvolume":" 32","citation":{"mla":"Boeddeker, Christoph, et al. “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, Institute of Electrical and Electronics Engineers (IEEE), 2024, pp. 1185–97, doi:10.1109/taslp.2024.3350887.","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.","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={10.1109/taslp.2024.3350887}, 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} }","apa":"Boeddeker, C., Subramanian, A. S., Wichern, G., Haeb-Umbach, R., & Le Roux, J. (2024). TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 32, 1185–1197. https://doi.org/10.1109/taslp.2024.3350887","ama":"Boeddeker C, Subramanian AS, Wichern G, Haeb-Umbach R, Le Roux J. TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2024;32:1185-1197. doi:10.1109/taslp.2024.3350887","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.” IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024): 1185–97. https://doi.org/10.1109/taslp.2024.3350887.","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,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 1185–1197, 2024, doi: 10.1109/taslp.2024.3350887."},"has_accepted_license":"1","publication_identifier":{"issn":["2329-9290","2329-9304"]},"publication_status":"published","doi":"10.1109/taslp.2024.3350887","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2303.03849"}],"oa":"1","date_updated":"2025-04-16T10:21:45Z","volume":32,"author":[{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"last_name":"Subramanian","full_name":"Subramanian, Aswin Shanmugam","first_name":"Aswin Shanmugam"},{"first_name":"Gordon","full_name":"Wichern, Gordon","last_name":"Wichern"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"},{"first_name":"Jonathan","full_name":"Le Roux, Jonathan","last_name":"Le Roux"}],"status":"public","type":"journal_article","file_date_updated":"2025-04-16T10:21:45Z","_id":"52958","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"448568305","_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"department":[{"_id":"54"}],"user_id":"40767"},{"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":[{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","full_name":"von Neumann, Thilo","id":"49870","first_name":"Thilo"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr","first_name":"Tobias"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_updated":"2025-02-12T09:20:07Z","oa":"1","publisher":"IEEE","citation":{"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: 10.1109/icasspw62465.2024.10625894.","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 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). IEEE, 2024. https://doi.org/10.1109/icasspw62465.2024.10625894.","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: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). IEEE; 2024. doi:10.1109/icasspw62465.2024.10625894","apa":"von Neumann, T., Boeddeker, C., Cord-Landwehr, T., Delcroix, M., & Haeb-Umbach, R. (2024). Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). https://doi.org/10.1109/icasspw62465.2024.10625894","mla":"von Neumann, Thilo, et al. “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization.” 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2024, doi:10.1109/icasspw62465.2024.10625894.","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.","bibtex":"@inproceedings{von Neumann_Boeddeker_Cord-Landwehr_Delcroix_Haeb-Umbach_2024, title={Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization}, DOI={10.1109/icasspw62465.2024.10625894}, 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} }"},"year":"2024","publication_status":"published","has_accepted_license":"1","file_date_updated":"2024-09-04T07:34:30Z","language":[{"iso":"eng"}],"ddc":["000"],"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":"56004","file":[{"relation":"main_file","content_type":"application/pdf","file_size":150432,"file_name":"main.pdf","access_level":"open_access","file_id":"56005","date_updated":"2024-09-04T07:34:30Z","creator":"tvn","date_created":"2024-09-04T07:34:30Z"}],"status":"public","type":"conference","publication":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"},{"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"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"_id":"56272","user_id":"40767","department":[{"_id":"54"}],"year":"2024","citation":{"ieee":"C. Boeddeker, T. Cord-Landwehr, and R. Haeb-Umbach, “Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment,” 2024, doi: 10.21437/interspeech.2024-1286.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach. “Once More Diarization: Improving Meeting Transcription Systems through Segment-Level Speaker Reassignment.” In Interspeech 2024. ISCA, 2024. https://doi.org/10.21437/interspeech.2024-1286.","ama":"Boeddeker C, Cord-Landwehr T, Haeb-Umbach R. Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment. In: Interspeech 2024. ISCA; 2024. doi:10.21437/interspeech.2024-1286","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_Haeb-Umbach_2024, title={Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment}, DOI={10.21437/interspeech.2024-1286}, booktitle={Interspeech 2024}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2024} }","short":"C. Boeddeker, T. Cord-Landwehr, R. Haeb-Umbach, in: Interspeech 2024, ISCA, 2024.","mla":"Boeddeker, Christoph, et al. “Once More Diarization: Improving Meeting Transcription Systems through Segment-Level Speaker Reassignment.” Interspeech 2024, ISCA, 2024, doi:10.21437/interspeech.2024-1286.","apa":"Boeddeker, C., Cord-Landwehr, T., & Haeb-Umbach, R. (2024). Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment. Interspeech 2024. https://doi.org/10.21437/interspeech.2024-1286"},"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","author":[{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_created":"2024-09-30T08:04:47Z"},{"main_file_link":[{"open_access":"1","url":"https://www-i6.informatik.rwth-aachen.de/publications/download/1259/VietingPeterBergerSimonNeumannThilovonBoeddekerChristophSchl%FCterRalfHaeb-UmbachReinhold--CombiningTF-GridNetMixtureEncoderforContinuousSpeechSeparationforMeetingTranscription--2024.pdf"}],"title":"Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription","date_created":"2024-12-09T11:46:18Z","author":[{"full_name":"Vieting, Peter","last_name":"Vieting","first_name":"Peter"},{"last_name":"Berger","full_name":"Berger, Simon","first_name":"Simon"},{"first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Ralf","full_name":"Schlüter, Ralf","last_name":"Schlüter"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_updated":"2025-02-12T09:20:59Z","oa":"1","citation":{"apa":"Vieting, P., Berger, S., von Neumann, T., Boeddeker, C., Schlüter, R., & Haeb-Umbach, R. (2024). Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription. 2024 IEEE Spoken Language Technology Workshop (SLT).","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.” 2024 IEEE Spoken Language Technology Workshop (SLT), 2024.","short":"P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: 2024 IEEE Spoken Language Technology Workshop (SLT), 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 2024 IEEE Spoken Language Technology Workshop (SLT), 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: 2024 IEEE Spoken Language Technology Workshop (SLT). ; 2024."},"year":"2024","language":[{"iso":"eng"}],"department":[{"_id":"54"}],"user_id":"40767","_id":"57659","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"}],"status":"public","publication":"2024 IEEE Spoken Language Technology Workshop (SLT)","type":"conference"},{"status":"public","type":"conference","file_date_updated":"2025-08-14T08:11:57Z","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"}],"citation":{"bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Haeb-Umbach_2024, title={Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models}, DOI={10.1109/ICASSP49660.2025.10888445}, 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} }","mla":"Cord-Landwehr, Tobias, et al. “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models.” ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, doi:10.1109/ICASSP49660.2025.10888445.","short":"T. Cord-Landwehr, C. Boeddeker, R. Haeb-Umbach, in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.","apa":"Cord-Landwehr, T., Boeddeker, C., & Haeb-Umbach, R. (2024). Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India. https://doi.org/10.1109/ICASSP49660.2025.10888445","ama":"Cord-Landwehr T, Boeddeker C, Haeb-Umbach R. Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). ; 2024. doi:10.1109/ICASSP49660.2025.10888445","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: 10.1109/ICASSP49660.2025.10888445.","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models.” In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. https://doi.org/10.1109/ICASSP49660.2025.10888445."},"has_accepted_license":"1","conference":{"name":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India"},"doi":"10.1109/ICASSP49660.2025.10888445","main_file_link":[{"open_access":"1","url":"https://arxiv.org/pdf/2410.21455"}],"author":[{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-08-14T08:12:22Z","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","access_level":"closed","file_name":"main.pdf","file_id":"60930","file_size":259907,"creator":"cord","date_created":"2025-08-14T08:11:57Z","date_updated":"2025-08-14T08:11:57Z"}],"abstract":[{"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.","lang":"eng"}],"publication":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","language":[{"iso":"eng"}],"keyword":["diarization","source separation","mixture model","meeting"],"ddc":["000"],"year":"2024","title":"Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models","date_created":"2024-11-14T09:32:38Z"},{"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":[{"file_id":"60929","access_level":"closed","file_name":"main.pdf","file_size":254478,"date_created":"2025-08-14T08:09:52Z","creator":"cord","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)","language":[{"iso":"eng"}],"ddc":["000"],"citation":{"apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., & Haeb-Umbach, R. (2024). Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul. https://doi.org/10.1109/icassp48485.2024.10445911","mla":"Cord-Landwehr, Tobias, et al. “Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios.” ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2024, doi:10.1109/icassp48485.2024.10445911.","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={10.1109/icassp48485.2024.10445911}, 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.","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: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2024. doi:10.1109/icassp48485.2024.10445911","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 ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024. https://doi.org/10.1109/icassp48485.2024.10445911.","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: 10.1109/icassp48485.2024.10445911."},"publication_status":"published","has_accepted_license":"1","conference":{"location":"Seoul","name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},"doi":"10.1109/icassp48485.2024.10445911","author":[{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"last_name":"Zorilă","full_name":"Zorilă, Cătălin","first_name":"Cătălin"},{"full_name":"Doddipatla, Rama","last_name":"Doddipatla","first_name":"Rama"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_updated":"2025-08-14T08:11:07Z","status":"public","type":"conference","file_date_updated":"2025-08-14T08:09:52Z","user_id":"44393","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"}],"_id":"53659"},{"language":[{"iso":"eng"}],"_id":"48391","user_id":"40767","department":[{"_id":"54"}],"status":"public","type":"conference","publication":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","title":"Reverberation as Supervision For Speech Separation","doi":"10.1109/icassp49357.2023.10095022","publisher":"IEEE","date_updated":"2023-10-23T15:10:16Z","author":[{"first_name":"Rohith","full_name":"Aralikatti, Rohith","last_name":"Aralikatti"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"first_name":"Gordon","full_name":"Wichern, Gordon","last_name":"Wichern"},{"full_name":"Subramanian, Aswin","last_name":"Subramanian","first_name":"Aswin"},{"first_name":"Jonathan","full_name":"Le Roux, Jonathan","last_name":"Le Roux"}],"date_created":"2023-10-23T15:09:13Z","year":"2023","citation":{"bibtex":"@inproceedings{Aralikatti_Boeddeker_Wichern_Subramanian_Le Roux_2023, title={Reverberation as Supervision For Speech Separation}, DOI={10.1109/icassp49357.2023.10095022}, booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Aralikatti, Rohith and Boeddeker, Christoph and Wichern, Gordon and Subramanian, Aswin and Le Roux, Jonathan}, year={2023} }","mla":"Aralikatti, Rohith, et al. “Reverberation as Supervision For Speech Separation.” ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, doi:10.1109/icassp49357.2023.10095022.","short":"R. Aralikatti, C. Boeddeker, G. Wichern, A. Subramanian, J. Le Roux, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023.","apa":"Aralikatti, R., Boeddeker, C., Wichern, G., Subramanian, A., & Le Roux, J. (2023). Reverberation as Supervision For Speech Separation. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10095022","ama":"Aralikatti R, Boeddeker C, Wichern G, Subramanian A, Le Roux J. Reverberation as Supervision For Speech Separation. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. doi:10.1109/icassp49357.2023.10095022","chicago":"Aralikatti, Rohith, Christoph Boeddeker, Gordon Wichern, Aswin Subramanian, and Jonathan Le Roux. “Reverberation as Supervision For Speech Separation.” In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023. https://doi.org/10.1109/icassp49357.2023.10095022.","ieee":"R. Aralikatti, C. Boeddeker, G. Wichern, A. Subramanian, and J. Le Roux, “Reverberation as Supervision For Speech Separation,” 2023, doi: 10.1109/icassp49357.2023.10095022."},"publication_status":"published"},{"publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","file":[{"date_created":"2023-01-09T17:46:05Z","creator":"haebumb","date_updated":"2023-01-11T08:50:19Z","file_id":"35607","access_level":"open_access","file_name":"main.pdf","file_size":7185077,"content_type":"application/pdf","relation":"main_file"}],"abstract":[{"text":"Continuous Speech Separation (CSS) has been proposed to address speech overlaps during the analysis of realistic meeting-like conversations by eliminating any overlaps before further processing.\r\nCSS separates a recording of arbitrarily many speakers into a small number of overlap-free output channels, where each output channel may contain speech of multiple speakers.\r\nThis is often done by applying a conventional separation model trained with Utterance-level Permutation Invariant Training (uPIT), which exclusively maps a speaker to an output channel, in sliding window approach called stitching.\r\nRecently, we introduced an alternative training scheme called Graph-PIT that teaches the separation network to directly produce output streams in the required format without stitching.\r\nIt can handle an arbitrary number of speakers as long as never more of them overlap at the same time than the separator has output channels.\r\nIn this contribution, we further investigate the Graph-PIT training scheme.\r\nWe show in extended experiments that models trained with Graph-PIT also work in challenging reverberant conditions.\r\nModels trained in this way are able to perform segment-less CSS, i.e., without stitching, and achieve comparable and often better separation quality than the conventional CSS with uPIT and stitching.\r\nWe simplify the training schedule for Graph-PIT with the recently proposed Source Aggregated Signal-to-Distortion Ratio (SA-SDR) loss.\r\nIt eliminates unfavorable properties of the previously used A-SDR loss and thus enables training with Graph-PIT from scratch.\r\nGraph-PIT training relaxes the constraints w.r.t. the allowed numbers of speakers and speaking patterns which allows using a larger variety of training data.\r\nFurthermore, we introduce novel signal-level evaluation metrics for meeting scenarios, namely the source-aggregated scale- and convolution-invariant Signal-to-Distortion Ratio (SA-SI-SDR and SA-CI-SDR), which are generalizations of the commonly used SDR-based metrics for the CSS case.","lang":"eng"}],"language":[{"iso":"eng"}],"ddc":["000"],"keyword":["Continuous Speech Separation","Source Separation","Graph-PIT","Dynamic Programming","Permutation Invariant Training"],"quality_controlled":"1","year":"2023","date_created":"2023-01-09T17:24:17Z","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","title":"Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria","type":"journal_article","status":"public","user_id":"49870","department":[{"_id":"54"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"35602","file_date_updated":"2023-01-11T08:50:19Z","article_type":"original","publication_status":"published","has_accepted_license":"1","publication_identifier":{"issn":["2329-9290","2329-9304"]},"citation":{"ieee":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 576–589, 2023, doi: 10.1109/taslp.2022.3228629.","chicago":"Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach. “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria.” IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023): 576–89. https://doi.org/10.1109/taslp.2022.3228629.","ama":"von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2023;31:576-589. doi:10.1109/taslp.2022.3228629","apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2023). Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 576–589. https://doi.org/10.1109/taslp.2022.3228629","bibtex":"@article{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2023, title={Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria}, volume={31}, DOI={10.1109/taslp.2022.3228629}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2023}, pages={576–589} }","short":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023) 576–589.","mla":"von Neumann, Thilo, et al. “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, Institute of Electrical and Electronics Engineers (IEEE), 2023, pp. 576–89, doi:10.1109/taslp.2022.3228629."},"page":"576-589","intvolume":" 31","author":[{"id":"49870","full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","first_name":"Thilo"},{"first_name":"Keisuke","full_name":"Kinoshita, Keisuke","last_name":"Kinoshita"},{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"volume":31,"oa":"1","date_updated":"2023-11-15T12:16:11Z","doi":"10.1109/taslp.2022.3228629"},{"quality_controlled":"1","year":"2023","publisher":"IEEE","date_created":"2023-10-19T07:38:31Z","title":"On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems","publication":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","abstract":[{"lang":"eng","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."}],"file":[{"file_size":204994,"file_name":"ICASSP_2023_Meeting_Evaluation.pdf","file_id":"48282","access_level":"open_access","date_updated":"2023-10-19T07:41:56Z","creator":"tvn","date_created":"2023-10-19T07:39:57Z","relation":"main_file","content_type":"application/pdf"}],"ddc":["000"],"keyword":["Word Error Rate","Meeting Recognition","Levenshtein Distance"],"language":[{"iso":"eng"}],"publication_status":"published","has_accepted_license":"1","related_material":{"link":[{"relation":"software","url":"https://github.com/fgnt/meeteval"}]},"citation":{"apa":"von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., & Haeb-Umbach, R. (2023). On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10094784","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={10.1109/icassp49357.2023.10094784}, 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} }","mla":"von Neumann, Thilo, et al. “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems.” ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, doi:10.1109/icassp49357.2023.10094784.","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.","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 ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023. https://doi.org/10.1109/icassp49357.2023.10094784.","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: 10.1109/icassp49357.2023.10094784.","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: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. doi:10.1109/icassp49357.2023.10094784"},"oa":"1","date_updated":"2025-02-12T09:16:34Z","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":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10094784"}],"doi":"10.1109/icassp49357.2023.10094784","type":"conference","status":"public","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"}],"_id":"48281","user_id":"40767","department":[{"_id":"54"}],"file_date_updated":"2023-10-19T07:41:56Z"},{"conference":{"location":"Dublin","name":"CHiME 2023 Workshop on Speech Processing in Everyday Environments"},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2307.11394"}],"date_updated":"2025-02-12T09:12:05Z","oa":"1","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":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"last_name":"Delcroix","full_name":"Delcroix, Marc","first_name":"Marc"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"citation":{"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.” Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.","short":"T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.","apa":"von Neumann, T., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2023). MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments. CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin.","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.","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 Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 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: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments. ; 2023."},"has_accepted_license":"1","related_material":{"link":[{"url":"https://github.com/fgnt/meeteval","relation":"software"}]},"file_date_updated":"2023-10-19T07:19:59Z","_id":"48275","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","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","keyword":["Speech Recognition","Word Error Rate","Meeting Transcription"],"ddc":["000"],"language":[{"iso":"eng"}],"abstract":[{"lang":"eng","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."}],"file":[{"relation":"main_file","content_type":"application/pdf","file_name":"Chime_7__MeetEval.pdf","access_level":"open_access","file_id":"48276","file_size":263744,"creator":"tvn","date_created":"2023-10-19T07:19:59Z","date_updated":"2023-10-19T07:19:59Z"}],"publication":"Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments"},{"ddc":["000"],"language":[{"iso":"eng"}],"file":[{"date_updated":"2023-11-15T14:56:18Z","date_created":"2023-11-15T14:56:18Z","creator":"cord","file_size":246306,"file_name":"teacher_student_embeddings.pdf","file_id":"48932","access_level":"open_access","content_type":"application/pdf","relation":"main_file"}],"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","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"},{"grant_number":"448568305","_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"department":[{"_id":"54"}],"user_id":"40767","status":"public","type":"conference","conference":{"location":"Rhodes","name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},"doi":"10.1109/icassp49357.2023.10095370","date_updated":"2025-02-12T09:14:45Z","oa":"1","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"},{"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: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. doi:10.1109/icassp49357.2023.10095370","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: 10.1109/icassp49357.2023.10095370.","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 ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023. https://doi.org/10.1109/icassp49357.2023.10095370.","mla":"Cord-Landwehr, Tobias, et al. “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.” ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, doi:10.1109/icassp49357.2023.10095370.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization}, DOI={10.1109/icassp49357.2023.10095370}, 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., & Haeb-Umbach, R. (2023). Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes. https://doi.org/10.1109/icassp49357.2023.10095370"},"has_accepted_license":"1","publication_status":"published"},{"publication_status":"published","has_accepted_license":"1","citation":{"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 INTERSPEECH 2023. ISCA, 2023. https://doi.org/10.21437/interspeech.2023-1379.","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: 10.21437/interspeech.2023-1379.","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: INTERSPEECH 2023. ISCA; 2023. doi:10.21437/interspeech.2023-1379","mla":"Cord-Landwehr, Tobias, et al. “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures.” INTERSPEECH 2023, ISCA, 2023, doi:10.21437/interspeech.2023-1379.","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={10.21437/interspeech.2023-1379}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2023} }","apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., & Haeb-Umbach, R. (2023). A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. INTERSPEECH 2023. https://doi.org/10.21437/interspeech.2023-1379"},"year":"2023","date_created":"2023-09-19T14:34:37Z","author":[{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"full_name":"Zorilă, Cătălin","last_name":"Zorilă","first_name":"Cătălin"},{"first_name":"Rama","last_name":"Doddipatla","full_name":"Doddipatla, Rama"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-02-12T09:15:28Z","publisher":"ISCA","doi":"10.21437/interspeech.2023-1379","title":"A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures","type":"conference","publication":"INTERSPEECH 2023","file":[{"relation":"main_file","content_type":"application/pdf","file_size":303203,"access_level":"open_access","file_name":"multispeaker_embeddings.pdf","file_id":"48933","date_updated":"2023-11-15T15:00:02Z","date_created":"2023-11-15T15:00:02Z","creator":"cord"}],"status":"public","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":"47129","file_date_updated":"2023-11-15T15:00:02Z","language":[{"iso":"eng"}],"ddc":["000"]},{"publication_status":"published","citation":{"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.” 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023), ISCA, 2023, doi:10.21437/chime.2023-10.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2023, title={Multi-stage diarization refinement for the CHiME-7 DASR scenario}, DOI={10.21437/chime.2023-10}, 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., & Haeb-Umbach, R. (2023). Multi-stage diarization refinement for the CHiME-7 DASR scenario. 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023). https://doi.org/10.21437/chime.2023-10","ama":"Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. Multi-stage diarization refinement for the CHiME-7 DASR scenario. In: 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023). ISCA; 2023. doi:10.21437/chime.2023-10","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: 10.21437/chime.2023-10.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.” In 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023). ISCA, 2023. https://doi.org/10.21437/chime.2023-10."},"year":"2023","date_created":"2024-05-23T15:16:15Z","author":[{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Tobias","last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, 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"}],"date_updated":"2025-02-12T09:16:13Z","oa":"1","publisher":"ISCA","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/chime_2023/boeddeker23_chime.pdf"}],"doi":"10.21437/chime.2023-10","title":"Multi-stage diarization refinement for the CHiME-7 DASR scenario","type":"conference","publication":"7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)","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":"54439","language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"project":[{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"_id":"48390","user_id":"40767","department":[{"_id":"54"}],"status":"public","type":"conference","publication":"INTERSPEECH 2023","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","date_updated":"2025-02-12T09:11:30Z","oa":"1","publisher":"ISCA","date_created":"2023-10-23T15:06:39Z","author":[{"full_name":"Berger, Simon","last_name":"Berger","first_name":"Simon"},{"last_name":"Vieting","full_name":"Vieting, Peter","first_name":"Peter"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Ralf","full_name":"Schlüter, Ralf","last_name":"Schlüter"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"year":"2023","citation":{"ama":"Berger S, Vieting P, Boeddeker C, Schlüter R, Haeb-Umbach R. Mixture Encoder for Joint Speech Separation and Recognition. In: INTERSPEECH 2023. ISCA; 2023. doi:10.21437/interspeech.2023-1815","ieee":"S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach, “Mixture Encoder for Joint Speech Separation and Recognition,” 2023, doi: 10.21437/interspeech.2023-1815.","chicago":"Berger, Simon, Peter Vieting, Christoph Boeddeker, Ralf Schlüter, and Reinhold Haeb-Umbach. “Mixture Encoder for Joint Speech Separation and Recognition.” In INTERSPEECH 2023. ISCA, 2023. https://doi.org/10.21437/interspeech.2023-1815.","short":"S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.","mla":"Berger, Simon, et al. “Mixture Encoder for Joint Speech Separation and Recognition.” INTERSPEECH 2023, ISCA, 2023, doi:10.21437/interspeech.2023-1815.","bibtex":"@inproceedings{Berger_Vieting_Boeddeker_Schlüter_Haeb-Umbach_2023, title={Mixture Encoder for Joint Speech Separation and Recognition}, DOI={10.21437/interspeech.2023-1815}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Berger, Simon and Vieting, Peter and Boeddeker, Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2023} }","apa":"Berger, S., Vieting, P., Boeddeker, C., Schlüter, R., & Haeb-Umbach, R. (2023). Mixture Encoder for Joint Speech Separation and Recognition. INTERSPEECH 2023. https://doi.org/10.21437/interspeech.2023-1815"},"publication_status":"published"},{"date_created":"2022-10-11T07:27:51Z","title":"End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party","year":"2022","language":[{"iso":"eng"}],"ddc":["000"],"publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","file":[{"file_id":"33674","file_name":"End-to-End_Dereverberation_Beamforming_and_Speech_Recognition_in_A_Cocktail_Party.pdf","access_level":"open_access","relation":"main_file","file_size":6167931,"creator":"huesera","date_created":"2022-10-11T07:23:13Z","content_type":"application/pdf","date_updated":"2022-10-11T07:23:13Z"}],"abstract":[{"text":"Far-field multi-speaker automatic speech recognition (ASR) has drawn increasing attention in recent years. Most existing methods feature a signal processing frontend and an ASR backend. In realistic scenarios, these modules are usually trained separately or progressively, which suffers from either inter-module mismatch or a complicated training process. In this paper, we propose an end-to-end multi-channel model that jointly optimizes the speech enhancement (including speech dereverberation, denoising, and separation) frontend and the ASR backend as a single system. To the best of our knowledge, this is the first work that proposes to optimize dereverberation, beamforming, and multi-speaker ASR in a fully end-to-end manner. The frontend module consists of a weighted prediction error (WPE) based submodule for dereverberation and a neural beamformer for denoising and speech separation. For the backend, we adopt a widely used end-to-end (E2E) ASR architecture. It is worth noting that the entire model is differentiable and can be optimized in a fully end-to-end manner using only the ASR criterion, without the need of parallel signal-level labels. We evaluate the proposed model on several multi-speaker benchmark datasets, and experimental results show that the fully E2E ASR model can achieve competitive performance on both noisy and reverberant conditions, with over 30% relative word error rate (WER) reduction over the single-channel baseline systems.","lang":"eng"}],"author":[{"first_name":"Wangyou","full_name":"Zhang, Wangyou","last_name":"Zhang"},{"last_name":"Chang","full_name":"Chang, Xuankai","first_name":"Xuankai"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"last_name":"Nakatani","full_name":"Nakatani, Tomohiro","first_name":"Tomohiro"},{"first_name":"Shinji","full_name":"Watanabe, Shinji","last_name":"Watanabe"},{"first_name":"Yanmin","full_name":"Qian, Yanmin","last_name":"Qian"}],"oa":"1","date_updated":"2022-12-05T12:35:31Z","doi":"10.1109/TASLP.2022.3209942","related_material":{"link":[{"relation":"confirmation","url":"https://ieeexplore.ieee.org/abstract/document/9904314"}]},"publication_identifier":{"issn":["Print ISSN: 2329-9290 Electronic ISSN: 2329-9304"]},"has_accepted_license":"1","publication_status":"published","citation":{"ama":"Zhang W, Chang X, Boeddeker C, Nakatani T, Watanabe S, Qian Y. End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party. IEEE/ACM Transactions on Audio, Speech, and Language Processing. Published online 2022. doi:10.1109/TASLP.2022.3209942","chicago":"Zhang, Wangyou, Xuankai Chang, Christoph Boeddeker, Tomohiro Nakatani, Shinji Watanabe, and Yanmin Qian. “End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022. https://doi.org/10.1109/TASLP.2022.3209942.","ieee":"W. Zhang, X. Chang, C. Boeddeker, T. Nakatani, S. Watanabe, and Y. Qian, “End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, doi: 10.1109/TASLP.2022.3209942.","mla":"Zhang, Wangyou, et al. “End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, doi:10.1109/TASLP.2022.3209942.","short":"W. Zhang, X. Chang, C. Boeddeker, T. Nakatani, S. Watanabe, Y. Qian, IEEE/ACM Transactions on Audio, Speech, and Language Processing (2022).","bibtex":"@article{Zhang_Chang_Boeddeker_Nakatani_Watanabe_Qian_2022, title={End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party}, DOI={10.1109/TASLP.2022.3209942}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, author={Zhang, Wangyou and Chang, Xuankai and Boeddeker, Christoph and Nakatani, Tomohiro and Watanabe, Shinji and Qian, Yanmin}, year={2022} }","apa":"Zhang, W., Chang, X., Boeddeker, C., Nakatani, T., Watanabe, S., & Qian, Y. (2022). End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party. IEEE/ACM Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/TASLP.2022.3209942"},"department":[{"_id":"54"}],"user_id":"40767","_id":"33669","file_date_updated":"2022-10-11T07:23:13Z","type":"journal_article","status":"public"},{"file_date_updated":"2023-11-15T14:54:56Z","user_id":"44393","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"33847","status":"public","type":"conference","conference":{"location":"Bamberg","name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"author":[{"full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr","first_name":"Tobias"},{"first_name":"Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","full_name":"von Neumann, Thilo","id":"49870"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"oa":"1","date_updated":"2023-11-15T14:55:14Z","citation":{"ama":"Cord-Landwehr T, von Neumann T, Boeddeker C, Haeb-Umbach R. MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. In: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). ; 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 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 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.","short":"T. Cord-Landwehr, T. von Neumann, C. Boeddeker, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.","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} }","mla":"Cord-Landwehr, Tobias, et al. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.” 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.","apa":"Cord-Landwehr, T., von Neumann, T., Boeddeker, C., & Haeb-Umbach, R. (2022). MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg."},"has_accepted_license":"1","language":[{"iso":"eng"}],"ddc":["000"],"external_id":{"arxiv":["2209.11494"]},"file":[{"access_level":"open_access","file_name":"mms_msg_camera_ready.pdf","file_id":"48931","file_size":177975,"creator":"cord","date_created":"2023-11-15T14:54:56Z","date_updated":"2023-11-15T14:54:56Z","relation":"main_file","content_type":"application/pdf"}],"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"}],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","title":"MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator","date_created":"2022-10-20T14:02:14Z","year":"2022","quality_controlled":"1"},{"ddc":["000"],"language":[{"iso":"eng"}],"external_id":{"arxiv":["2111.07578"]},"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":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2023-11-15T14:52:16Z","creator":"cord","date_created":"2023-11-15T14:52:16Z","file_size":212890,"file_id":"48930","access_level":"open_access","file_name":"monaural_source_separation.pdf"}],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","title":"Monaural source separation: From anechoic to reverberant environments","publisher":"IEEE","date_created":"2022-10-20T14:07:28Z","year":"2022","file_date_updated":"2023-11-15T14:52:16Z","_id":"33848","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","conference":{"name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"date_updated":"2025-02-12T09:05:25Z","oa":"1","author":[{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","full_name":"von Neumann, Thilo","id":"49870","first_name":"Thilo"},{"full_name":"Zorila, Catalin","last_name":"Zorila","first_name":"Catalin"},{"last_name":"Doddipatla","full_name":"Doddipatla, Rama","first_name":"Rama"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"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: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). 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 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). Bamberg: IEEE, 2022.","apa":"Cord-Landwehr, T., Boeddeker, C., von Neumann, T., Zorila, C., Doddipatla, R., & Haeb-Umbach, R. (2022). Monaural source separation: From anechoic to reverberant environments. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). 2022 International Workshop on Acoustic Signal Enhancement (IWAENC).","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.” 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 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."},"has_accepted_license":"1"},{"ddc":["000"],"language":[{"iso":"eng"}],"publication":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","file":[{"relation":"main_file","content_type":"application/pdf","file_size":228069,"file_id":"33820","access_level":"open_access","file_name":"main.pdf","date_updated":"2022-10-20T05:33:10Z","date_created":"2022-10-20T05:33:10Z","creator":"tvn"},{"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"}],"publisher":"IEEE","date_created":"2022-10-20T05:29:12Z","title":"SA-SDR: A Novel Loss Function for Separation of Meeting Style Data","quality_controlled":"1","year":"2022","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","user_id":"40767","department":[{"_id":"54"}],"file_date_updated":"2022-10-20T05:35:32Z","type":"conference","status":"public","date_updated":"2025-02-12T09:08:14Z","oa":"1","author":[{"last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo"},{"last_name":"Kinoshita","full_name":"Kinoshita, Keisuke","first_name":"Keisuke"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"doi":"10.1109/icassp43922.2022.9746757","publication_status":"published","has_accepted_license":"1","related_material":{"link":[{"relation":"supplementary_material","url":"https://github.com/fgnt/graph_pit"}]},"citation":{"apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2022). SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9746757","bibtex":"@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2022, title={SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}, DOI={10.1109/icassp43922.2022.9746757}, 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} }","mla":"von Neumann, Thilo, et al. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022, doi:10.1109/icassp43922.2022.9746757.","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.","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: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2022. doi:10.1109/icassp43922.2022.9746757","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: 10.1109/icassp43922.2022.9746757.","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 ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022. https://doi.org/10.1109/icassp43922.2022.9746757."}},{"year":"2022","citation":{"apa":"Gburrek, T., Boeddeker, C., von Neumann, T., Cord-Landwehr, T., Schmalenstroeer, J., & Haeb-Umbach, R. (2022). A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network. arXiv. https://doi.org/10.48550/ARXIV.2205.00944","mla":"Gburrek, Tobias, et al. A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network. arXiv, 2022, doi:10.48550/ARXIV.2205.00944.","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={10.48550/ARXIV.2205.00944}, 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.","chicago":"Gburrek, Tobias, Christoph Boeddeker, Thilo von Neumann, Tobias Cord-Landwehr, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network. arXiv, 2022. https://doi.org/10.48550/ARXIV.2205.00944.","ieee":"T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer, and 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. A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network. arXiv; 2022. doi:10.48550/ARXIV.2205.00944"},"has_accepted_license":"1","title":"A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network","doi":"10.48550/ARXIV.2205.00944","date_updated":"2025-02-12T09:03:42Z","publisher":"arXiv","oa":"1","author":[{"first_name":"Tobias","last_name":"Gburrek","id":"44006","full_name":"Gburrek, Tobias"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"first_name":"Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","id":"49870","full_name":"von Neumann, Thilo"},{"full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr","first_name":"Tobias"},{"last_name":"Schmalenstroeer","full_name":"Schmalenstroeer, Joerg","id":"460","first_name":"Joerg"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2022-10-18T11:10:58Z","status":"public","file":[{"content_type":"application/pdf","relation":"main_file","creator":"tgburrek","date_created":"2023-11-17T06:42:04Z","date_updated":"2023-11-17T06:42:04Z","access_level":"open_access","file_id":"48992","file_name":"meeting_transcription_22.pdf","file_size":199006}],"type":"misc","ddc":["004"],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-17T06:42:04Z","_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"}]