[{"keyword":["diarization","source separation","mixture model","meeting"],"ddc":["000"],"language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"We propose an approach for simultaneous diarization and separation of meeting data. It consists of a complex Angular Central Gaussian Mixture Model (cACGMM) for speech source separation, and a von-Mises-Fisher Mixture Model (VMFMM) for diarization in a joint statistical framework. Through the integration, both spatial and spectral information are exploited for diarization and separation. We also develop a method for counting the number of active speakers in a segment of a meeting to support block-wise processing. While the total number of speakers in a meeting may be known, it is usually not known on a per-segment level. With the proposed speaker counting, joint diarization and source separation can be done segment-by-segment, and the permutation problem across segments is solved, thus allowing for block-online processing in the future. Experimental results on the LibriCSS meeting corpus show that the integrated approach outperforms a cascaded approach of diarization and speech enhancement in terms of WER, both on a per-segment and on a per-meeting level."}],"file":[{"success":1,"relation":"main_file","content_type":"application/pdf","file_size":259907,"file_name":"main.pdf","file_id":"60930","access_level":"closed","date_updated":"2025-08-14T08:11:57Z","date_created":"2025-08-14T08:11:57Z","creator":"cord"}],"publication":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","title":"Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models","date_created":"2024-11-14T09:32:38Z","year":"2024","file_date_updated":"2025-08-14T08:11:57Z","_id":"57085","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"department":[{"_id":"54"}],"user_id":"44393","status":"public","type":"conference","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"}],"date_updated":"2025-08-14T08:12:22Z","oa":"1","author":[{"full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr","first_name":"Tobias"},{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"citation":{"chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models.” In <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2024. <a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">https://doi.org/10.1109/ICASSP49660.2025.10888445</a>.","ieee":"T. Cord-Landwehr, C. Boeddeker, and R. Haeb-Umbach, “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models,” presented at the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2024, doi: <a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>.","ama":"Cord-Landwehr T, Boeddeker C, Haeb-Umbach R. Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models. In: <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2024. doi:<a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>","mla":"Cord-Landwehr, Tobias, et al. “Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models.” <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2024, doi:<a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Haeb-Umbach_2024, title={Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models}, DOI={<a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">10.1109/ICASSP49660.2025.10888445</a>}, booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2024} }","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., &#38; Haeb-Umbach, R. (2024). Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models. <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India. <a href=\"https://doi.org/10.1109/ICASSP49660.2025.10888445\">https://doi.org/10.1109/ICASSP49660.2025.10888445</a>"},"has_accepted_license":"1"},{"has_accepted_license":"1","citation":{"ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks,” presented at the 57th Asilomar Conference on Signals, Systems, and Computers, 2023.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks.” In <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>, 2023.","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks. In: <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>. ; 2023.","apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2023). Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks. <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>. 57th Asilomar Conference on Signals, Systems, and Computers.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2023, title={Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks}, booktitle={Proc. Asilomar Conference on Signals, Systems, and Computers}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2023} }","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: Proc. Asilomar Conference on Signals, Systems, and Computers, 2023.","mla":"Gburrek, Tobias, et al. “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks.” <i>Proc. Asilomar Conference on Signals, Systems, and Computers</i>, 2023."},"oa":"1","date_updated":"2023-11-22T07:58:49Z","author":[{"first_name":"Tobias","last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006"},{"first_name":"Joerg","id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"conference":{"end_date":"2023-11-01","start_date":"2023-10-31","name":"57th Asilomar Conference on Signals, Systems, and Computers"},"type":"conference","status":"public","_id":"49109","department":[{"_id":"54"}],"user_id":"460","file_date_updated":"2023-11-22T07:58:49Z","quality_controlled":"1","year":"2023","date_created":"2023-11-22T07:52:29Z","title":"Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks","publication":"Proc. Asilomar Conference on Signals, Systems, and Computers","abstract":[{"text":"We propose a diarization system, that estimates “who spoke when” based on spatial information, to be used as a front-end of a meeting transcription system running on the signals gathered from an acoustic sensor network (ASN). Although the\r\nspatial distribution of the microphones is advantageous, exploiting the spatial diversity for diarization and signal enhancement is challenging, because the microphones’ positions are typically unknown, and the recorded signals are initially unsynchronized in general. Here, we approach these issues by first blindly synchronizing the signals and then estimating time differences of arrival (TDOAs). The TDOA information is exploited to estimate the speakers’ activity, even in the presence of multiple speakers being simultaneously active. This speaker activity information serves as a guide for a spatial mixture model, on which basis the individual speaker’s signals are extracted via beamforming. Finally, the extracted signals are forwarded to a speech recognizer. Additionally, a novel initialization scheme for spatial mixture models based on the TDOA estimates is proposed. Experiments conducted on real recordings from the LibriWASN data set have shown that our proposed system is advantageous compared to a system using a spatial mixture model, which does not make use\r\nof external diarization information.","lang":"eng"}],"file":[{"relation":"main_file","content_type":"application/pdf","access_level":"open_access","file_id":"49110","file_name":"asilomar.pdf","file_size":212317,"creator":"schmalen","date_created":"2023-11-22T07:51:18Z","date_updated":"2023-11-22T07:58:49Z"}],"keyword":["Diarization","time difference of arrival","ad-hoc acoustic sensor network","meeting transcription"],"ddc":["004"],"language":[{"iso":"eng"}]},{"related_material":{"link":[{"url":"https://github.com/fgnt/meeteval","relation":"software"}]},"publication_status":"published","has_accepted_license":"1","citation":{"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>.","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} }","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.","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>","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>.","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>.","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>"},"author":[{"first_name":"Thilo","full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"full_name":"Kinoshita, Keisuke","last_name":"Kinoshita","first_name":"Keisuke"},{"first_name":"Marc","full_name":"Delcroix, Marc","last_name":"Delcroix"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-02-12T09:16:34Z","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10094784"}],"doi":"10.1109/icassp49357.2023.10094784","type":"conference","status":"public","user_id":"40767","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"_id":"48281","file_date_updated":"2023-10-19T07:41:56Z","quality_controlled":"1","year":"2023","date_created":"2023-10-19T07:38:31Z","publisher":"IEEE","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)","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"}],"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."}],"language":[{"iso":"eng"}],"ddc":["000"],"keyword":["Word Error Rate","Meeting Recognition","Levenshtein Distance"]},{"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2307.11394"}],"conference":{"name":"CHiME 2023 Workshop on Speech Processing in Everyday Environments","location":"Dublin"},"date_updated":"2025-02-12T09:12:05Z","oa":"1","author":[{"first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","full_name":"von Neumann, Thilo","id":"49870"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"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.","short":"T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.","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.","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.","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."},"has_accepted_license":"1","related_material":{"link":[{"relation":"software","url":"https://github.com/fgnt/meeteval"}]},"file_date_updated":"2023-10-19T07:19:59Z","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":"48275","user_id":"40767","department":[{"_id":"54"}],"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","ddc":["000"],"keyword":["Speech Recognition","Word Error Rate","Meeting Transcription"],"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_size":263744,"file_id":"48276","access_level":"open_access","file_name":"Chime_7__MeetEval.pdf","date_updated":"2023-10-19T07:19:59Z","creator":"tvn","date_created":"2023-10-19T07:19:59Z"}],"publication":"Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments"}]