[{"file_date_updated":"2023-11-22T07:58:49Z","_id":"49109","user_id":"460","department":[{"_id":"54"}],"status":"public","type":"conference","conference":{"end_date":"2023-11-01","name":"57th Asilomar Conference on Signals, Systems, and Computers","start_date":"2023-10-31"},"oa":"1","date_updated":"2023-11-22T07:58:49Z","author":[{"full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek","first_name":"Tobias"},{"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"}],"citation":{"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.","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.","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.","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.","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.","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."},"has_accepted_license":"1","ddc":["004"],"keyword":["Diarization","time difference of arrival","ad-hoc acoustic sensor network","meeting transcription"],"language":[{"iso":"eng"}],"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","file_name":"asilomar.pdf","access_level":"open_access","file_id":"49110","file_size":212317,"date_created":"2023-11-22T07:51:18Z","creator":"schmalen","date_updated":"2023-11-22T07:58:49Z"}],"publication":"Proc. Asilomar Conference on Signals, Systems, and Computers","title":"Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks","date_created":"2023-11-22T07:52:29Z","year":"2023","quality_controlled":"1"},{"citation":{"apa":"von Neumann, T., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2023). MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>. CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin.","bibtex":"@inproceedings{von Neumann_Boeddeker_Delcroix_Haeb-Umbach_2023, title={MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems}, booktitle={Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments}, author={von Neumann, Thilo and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2023} }","mla":"von Neumann, Thilo, et al. “MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems.” <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>, 2023.","short":"T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.","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.","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 <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>, 2023."},"related_material":{"link":[{"relation":"software","url":"https://github.com/fgnt/meeteval"}]},"has_accepted_license":"1","main_file_link":[{"url":"https://arxiv.org/abs/2307.11394","open_access":"1"}],"conference":{"name":"CHiME 2023 Workshop on Speech Processing in Everyday Environments","location":"Dublin"},"author":[{"first_name":"Thilo","full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"last_name":"Delcroix","full_name":"Delcroix, Marc","first_name":"Marc"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2025-02-12T09:12:05Z","oa":"1","status":"public","type":"conference","file_date_updated":"2023-10-19T07:19:59Z","user_id":"40767","department":[{"_id":"54"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"_id":"48275","year":"2023","quality_controlled":"1","title":"MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems","date_created":"2023-10-19T07:24:51Z","file":[{"date_updated":"2023-10-19T07:19:59Z","date_created":"2023-10-19T07:19:59Z","creator":"tvn","file_size":263744,"file_id":"48276","access_level":"open_access","file_name":"Chime_7__MeetEval.pdf","content_type":"application/pdf","relation":"main_file"}],"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."}],"publication":"Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments","language":[{"iso":"eng"}],"ddc":["000"],"keyword":["Speech Recognition","Word Error Rate","Meeting Transcription"]}]