[{"citation":{"apa":"von Neumann, T., Boeddeker, C., Cord-Landwehr, T., Delcroix, M., &#38; Haeb-Umbach, R. (2024). Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>. <a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">https://doi.org/10.1109/icasspw62465.2024.10625894</a>","short":"T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, R. Haeb-Umbach, in: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2024.","mla":"von Neumann, Thilo, et al. “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization.” <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>, IEEE, 2024, doi:<a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>.","bibtex":"@inproceedings{von Neumann_Boeddeker_Cord-Landwehr_Delcroix_Haeb-Umbach_2024, title={Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization}, DOI={<a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>}, booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, publisher={IEEE}, author={von Neumann, Thilo and Boeddeker, Christoph and Cord-Landwehr, Tobias and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2024} }","chicago":"Neumann, Thilo von, Christoph Boeddeker, Tobias Cord-Landwehr, Marc Delcroix, and Reinhold Haeb-Umbach. “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization.” In <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>. IEEE, 2024. <a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">https://doi.org/10.1109/icasspw62465.2024.10625894</a>.","ieee":"T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, and R. Haeb-Umbach, “Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization,” 2024, doi: <a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>.","ama":"von Neumann T, Boeddeker C, Cord-Landwehr T, Delcroix M, Haeb-Umbach R. Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization. In: <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)</i>. IEEE; 2024. doi:<a href=\"https://doi.org/10.1109/icasspw62465.2024.10625894\">10.1109/icasspw62465.2024.10625894</a>"},"year":"2024","has_accepted_license":"1","publication_status":"published","doi":"10.1109/icasspw62465.2024.10625894","title":"Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization","author":[{"last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Tobias","id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_created":"2024-09-04T07:26:02Z","publisher":"IEEE","date_updated":"2025-02-12T09:20:07Z","oa":"1","status":"public","file":[{"relation":"main_file","content_type":"application/pdf","file_id":"56005","access_level":"open_access","file_name":"main.pdf","file_size":150432,"date_created":"2024-09-04T07:34:30Z","creator":"tvn","date_updated":"2024-09-04T07:34:30Z"}],"publication":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","type":"conference","language":[{"iso":"eng"}],"file_date_updated":"2024-09-04T07:34:30Z","ddc":["000"],"department":[{"_id":"54"}],"user_id":"40767","_id":"56004","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"}]},{"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","author":[{"last_name":"Vieting","full_name":"Vieting, Peter","first_name":"Peter"},{"first_name":"Simon","last_name":"Berger","full_name":"Berger, Simon"},{"first_name":"Thilo","id":"49870","full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Ralf","full_name":"Schlüter, Ralf","last_name":"Schlüter"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2024-12-09T11:46:18Z","oa":"1","date_updated":"2025-02-12T09:20:59Z","citation":{"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} }","short":"P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: 2024 IEEE Spoken Language Technology Workshop (SLT), 2024.","mla":"Vieting, Peter, et al. “Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription.” <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>, 2024.","apa":"Vieting, P., Berger, S., von Neumann, T., Boeddeker, C., Schlüter, R., &#38; Haeb-Umbach, R. (2024). Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription. <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>.","chicago":"Vieting, Peter, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf Schlüter, and Reinhold Haeb-Umbach. “Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription.” In <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>, 2024.","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.","ama":"Vieting P, Berger S, von Neumann T, Boeddeker C, Schlüter R, Haeb-Umbach R. Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription. In: <i>2024 IEEE Spoken Language Technology Workshop (SLT)</i>. ; 2024."},"year":"2024","language":[{"iso":"eng"}],"department":[{"_id":"54"}],"user_id":"40767","_id":"57659","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"}],"status":"public","publication":"2024 IEEE Spoken Language Technology Workshop (SLT)","type":"conference"},{"date_updated":"2023-11-15T12:16:11Z","oa":"1","volume":31,"author":[{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Keisuke","full_name":"Kinoshita, Keisuke","last_name":"Kinoshita"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"doi":"10.1109/taslp.2022.3228629","has_accepted_license":"1","publication_identifier":{"issn":["2329-9290","2329-9304"]},"publication_status":"published","intvolume":"        31","page":"576-589","citation":{"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={<a href=\"https://doi.org/10.1109/taslp.2022.3228629\">10.1109/taslp.2022.3228629</a>}, 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.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, vol. 31, Institute of Electrical and Electronics Engineers (IEEE), 2023, pp. 576–89, doi:<a href=\"https://doi.org/10.1109/taslp.2022.3228629\">10.1109/taslp.2022.3228629</a>.","apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2023). Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, <i>31</i>, 576–589. <a href=\"https://doi.org/10.1109/taslp.2022.3228629\">https://doi.org/10.1109/taslp.2022.3228629</a>","ama":"von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>. 2023;31:576-589. doi:<a href=\"https://doi.org/10.1109/taslp.2022.3228629\">10.1109/taslp.2022.3228629</a>","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.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i> 31 (2023): 576–89. <a href=\"https://doi.org/10.1109/taslp.2022.3228629\">https://doi.org/10.1109/taslp.2022.3228629</a>.","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,” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, vol. 31, pp. 576–589, 2023, doi: <a href=\"https://doi.org/10.1109/taslp.2022.3228629\">10.1109/taslp.2022.3228629</a>."},"_id":"35602","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"54"}],"user_id":"49870","article_type":"original","file_date_updated":"2023-01-11T08:50:19Z","type":"journal_article","status":"public","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","date_created":"2023-01-09T17:24:17Z","title":"Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria","quality_controlled":"1","year":"2023","keyword":["Continuous Speech Separation","Source Separation","Graph-PIT","Dynamic Programming","Permutation Invariant Training"],"ddc":["000"],"language":[{"iso":"eng"}],"publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","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"}],"file":[{"content_type":"application/pdf","relation":"main_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}]},{"related_material":{"link":[{"relation":"software","url":"https://github.com/fgnt/meeteval"}]},"publication_status":"published","has_accepted_license":"1","citation":{"apa":"von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., &#38; Haeb-Umbach, R. (2023). On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">https://doi.org/10.1109/icassp49357.2023.10094784</a>","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.","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} }","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":[{"full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"first_name":"Keisuke","full_name":"Kinoshita, Keisuke","last_name":"Kinoshita"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_updated":"2025-02-12T09:16:34Z","oa":"1","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":[{"_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","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","access_level":"open_access","file_id":"48282","date_updated":"2023-10-19T07:41:56Z","date_created":"2023-10-19T07:39:57Z","creator":"tvn","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"]},{"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"},{"grant_number":"448568305","name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"_id":"48275","status":"public","type":"conference","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"},"author":[{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","full_name":"von Neumann, Thilo","id":"49870","first_name":"Thilo"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-02-12T09:12:05Z","citation":{"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.","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.","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."},"related_material":{"link":[{"url":"https://github.com/fgnt/meeteval","relation":"software"}]},"has_accepted_license":"1","language":[{"iso":"eng"}],"ddc":["000"],"keyword":["Speech Recognition","Word Error Rate","Meeting Transcription"],"file":[{"date_created":"2023-10-19T07:19:59Z","creator":"tvn","date_updated":"2023-10-19T07:19:59Z","file_id":"48276","access_level":"open_access","file_name":"Chime_7__MeetEval.pdf","file_size":263744,"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","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"},{"year":"2023","citation":{"apa":"Boeddeker, C., Cord-Landwehr, T., von Neumann, T., &#38; Haeb-Umbach, R. (2023). Multi-stage diarization refinement for the CHiME-7 DASR scenario. <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. <a href=\"https://doi.org/10.21437/chime.2023-10\">https://doi.org/10.21437/chime.2023-10</a>","short":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: 7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023), ISCA, 2023.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2023, title={Multi-stage diarization refinement for the CHiME-7 DASR scenario}, DOI={<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>}, booktitle={7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2023} }","mla":"Boeddeker, Christoph, et al. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.” <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>, ISCA, 2023, doi:<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>.","ama":"Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. Multi-stage diarization refinement for the CHiME-7 DASR scenario. In: <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>","ieee":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “Multi-stage diarization refinement for the CHiME-7 DASR scenario,” 2023, doi: <a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.” In <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/chime.2023-10\">https://doi.org/10.21437/chime.2023-10</a>."},"publication_status":"published","title":"Multi-stage diarization refinement for the CHiME-7 DASR scenario","main_file_link":[{"url":"https://www.isca-archive.org/chime_2023/boeddeker23_chime.pdf","open_access":"1"}],"doi":"10.21437/chime.2023-10","date_updated":"2025-02-12T09:16:13Z","oa":"1","publisher":"ISCA","author":[{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2024-05-23T15:16:15Z","status":"public","type":"conference","publication":"7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)","language":[{"iso":"eng"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"508","name":"Automatische Transkription von Gesprächssituationen","grant_number":"448568305"}],"_id":"54439","user_id":"40767","department":[{"_id":"54"}]},{"conference":{"location":"Bamberg","name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"author":[{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"first_name":"Thilo","full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2023-11-15T14:55:14Z","oa":"1","citation":{"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.” <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, 2022.","apa":"Cord-Landwehr, T., von Neumann, T., Boeddeker, C., &#38; Haeb-Umbach, R. (2022). MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg.","ieee":"T. Cord-Landwehr, T. von Neumann, C. Boeddeker, and R. Haeb-Umbach, “MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator,” presented at the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg, 2022.","chicago":"Cord-Landwehr, Tobias, Thilo von Neumann, Christoph Boeddeker, and Reinhold Haeb-Umbach. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, 2022.","ama":"Cord-Landwehr T, von Neumann T, Boeddeker C, Haeb-Umbach R. MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. ; 2022."},"has_accepted_license":"1","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","title":"MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator","date_created":"2022-10-20T14:02:14Z","year":"2022","quality_controlled":"1","language":[{"iso":"eng"}],"ddc":["000"],"external_id":{"arxiv":["2209.11494"]},"file":[{"access_level":"open_access","file_id":"48931","file_name":"mms_msg_camera_ready.pdf","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)"},{"type":"conference","status":"public","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"_id":"33848","user_id":"40767","department":[{"_id":"54"}],"file_date_updated":"2023-11-15T14:52:16Z","has_accepted_license":"1","place":"Bamberg","citation":{"bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_von Neumann_Zorila_Doddipatla_Haeb-Umbach_2022, place={Bamberg}, title={Monaural source separation: From anechoic to reverberant environments}, booktitle={2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Zorila, Catalin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2022} }","mla":"Cord-Landwehr, Tobias, et al. “Monaural Source Separation: From Anechoic to Reverberant Environments.” <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, IEEE, 2022.","short":"T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, Bamberg, 2022.","apa":"Cord-Landwehr, T., Boeddeker, C., von Neumann, T., Zorila, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2022). Monaural source separation: From anechoic to reverberant environments. <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC).","ieee":"T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla, and R. Haeb-Umbach, “Monaural source separation: From anechoic to reverberant environments,” presented at the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, and Reinhold Haeb-Umbach. “Monaural Source Separation: From Anechoic to Reverberant Environments.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. Bamberg: IEEE, 2022.","ama":"Cord-Landwehr T, Boeddeker C, von Neumann T, Zorila C, Doddipatla R, Haeb-Umbach R. Monaural source separation: From anechoic to reverberant environments. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE; 2022."},"date_updated":"2025-02-12T09:05:25Z","oa":"1","author":[{"first_name":"Tobias","last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Catalin","full_name":"Zorila, Catalin","last_name":"Zorila"},{"last_name":"Doddipatla","full_name":"Doddipatla, Rama","first_name":"Rama"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"conference":{"name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","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":[{"date_updated":"2023-11-15T14:52:16Z","creator":"cord","date_created":"2023-11-15T14:52:16Z","file_size":212890,"file_id":"48930","file_name":"monaural_source_separation.pdf","access_level":"open_access","content_type":"application/pdf","relation":"main_file"}],"external_id":{"arxiv":["2111.07578"]},"ddc":["000"],"language":[{"iso":"eng"}],"year":"2022","publisher":"IEEE","date_created":"2022-10-20T14:07:28Z","title":"Monaural source separation: From anechoic to reverberant environments"},{"doi":"10.1109/icassp43922.2022.9746757","date_updated":"2025-02-12T09:08:14Z","oa":"1","author":[{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"citation":{"ama":"von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. In: <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2022. doi:<a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>","ieee":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data,” 2022, doi: <a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>.","chicago":"Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” In <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2022. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">https://doi.org/10.1109/icassp43922.2022.9746757</a>.","mla":"von Neumann, Thilo, et al. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>.","bibtex":"@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2022, title={SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}, DOI={<a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022.","apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2022). SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">https://doi.org/10.1109/icassp43922.2022.9746757</a>"},"has_accepted_license":"1","publication_status":"published","related_material":{"link":[{"url":"https://github.com/fgnt/graph_pit","relation":"supplementary_material"}]},"file_date_updated":"2022-10-20T05:35:32Z","_id":"33819","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","title":"SA-SDR: A Novel Loss Function for Separation of Meeting Style Data","publisher":"IEEE","date_created":"2022-10-20T05:29:12Z","year":"2022","quality_controlled":"1","ddc":["000"],"language":[{"iso":"eng"}],"file":[{"file_name":"main.pdf","file_id":"33820","access_level":"open_access","file_size":228069,"creator":"tvn","date_created":"2022-10-20T05:33:10Z","date_updated":"2022-10-20T05:33:10Z","relation":"main_file","content_type":"application/pdf"},{"date_updated":"2022-10-20T05:35:32Z","creator":"tvn","date_created":"2022-10-20T05:35:32Z","file_size":229166,"file_name":"poster.pdf","file_id":"33821","access_level":"open_access","content_type":"application/pdf","relation":"poster"}],"publication":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"file":[{"file_id":"48992","access_level":"open_access","file_name":"meeting_transcription_22.pdf","file_size":199006,"date_created":"2023-11-17T06:42:04Z","creator":"tgburrek","date_updated":"2023-11-17T06:42:04Z","relation":"main_file","content_type":"application/pdf"}],"status":"public","type":"misc","language":[{"iso":"eng"}],"file_date_updated":"2023-11-17T06:42:04Z","ddc":["004"],"user_id":"40767","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Automatische Transkription von Gesprächssituationen","_id":"508","grant_number":"448568305"}],"_id":"33816","citation":{"ieee":"T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer, and R. Haeb-Umbach, <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv, 2022.","chicago":"Gburrek, Tobias, Christoph Boeddeker, Thilo von Neumann, Tobias Cord-Landwehr, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv, 2022. <a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">https://doi.org/10.48550/ARXIV.2205.00944</a>.","ama":"Gburrek T, Boeddeker C, von Neumann T, Cord-Landwehr T, Schmalenstroeer J, Haeb-Umbach R. <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv; 2022. doi:<a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">10.48550/ARXIV.2205.00944</a>","mla":"Gburrek, Tobias, et al. <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv, 2022, doi:<a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">10.48550/ARXIV.2205.00944</a>.","bibtex":"@book{Gburrek_Boeddeker_von Neumann_Cord-Landwehr_Schmalenstroeer_Haeb-Umbach_2022, title={A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network}, DOI={<a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">10.48550/ARXIV.2205.00944</a>}, publisher={arXiv}, author={Gburrek, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Cord-Landwehr, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer, R. Haeb-Umbach, A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network, arXiv, 2022.","apa":"Gburrek, T., Boeddeker, C., von Neumann, T., Cord-Landwehr, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2022). <i>A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network</i>. arXiv. <a href=\"https://doi.org/10.48550/ARXIV.2205.00944\">https://doi.org/10.48550/ARXIV.2205.00944</a>"},"year":"2022","has_accepted_license":"1","doi":"10.48550/ARXIV.2205.00944","title":"A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network","author":[{"last_name":"Gburrek","full_name":"Gburrek, Tobias","id":"44006","first_name":"Tobias"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Thilo","full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann"},{"last_name":"Cord-Landwehr","id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias"},{"first_name":"Joerg","full_name":"Schmalenstroeer, Joerg","id":"460","last_name":"Schmalenstroeer"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"date_created":"2022-10-18T11:10:58Z","publisher":"arXiv","date_updated":"2025-02-12T09:03:42Z","oa":"1"},{"type":"conference","publication":"Interspeech 2022","status":"public","user_id":"40767","department":[{"_id":"54"}],"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":"33954","language":[{"iso":"eng"}],"publication_status":"published","citation":{"apa":"Boeddeker, C., Cord-Landwehr, T., von Neumann, T., &#38; Haeb-Umbach, R. (2022). An Initialization Scheme for Meeting Separation with Spatial Mixture Models. <i>Interspeech 2022</i>. <a href=\"https://doi.org/10.21437/interspeech.2022-10929\">https://doi.org/10.21437/interspeech.2022-10929</a>","short":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: Interspeech 2022, ISCA, 2022.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2022, title={An Initialization Scheme for Meeting Separation with Spatial Mixture Models}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>}, booktitle={Interspeech 2022}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2022} }","mla":"Boeddeker, Christoph, et al. “An Initialization Scheme for Meeting Separation with Spatial Mixture Models.” <i>Interspeech 2022</i>, ISCA, 2022, doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>.","ieee":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “An Initialization Scheme for Meeting Separation with Spatial Mixture Models,” 2022, doi: <a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “An Initialization Scheme for Meeting Separation with Spatial Mixture Models.” In <i>Interspeech 2022</i>. ISCA, 2022. <a href=\"https://doi.org/10.21437/interspeech.2022-10929\">https://doi.org/10.21437/interspeech.2022-10929</a>.","ama":"Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. An Initialization Scheme for Meeting Separation with Spatial Mixture Models. In: <i>Interspeech 2022</i>. ISCA; 2022. doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10929\">10.21437/interspeech.2022-10929</a>"},"year":"2022","author":[{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr","first_name":"Tobias"},{"first_name":"Thilo","id":"49870","full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2022-10-28T10:53:56Z","oa":"1","date_updated":"2025-02-12T09:06:56Z","publisher":"ISCA","main_file_link":[{"open_access":"1","url":"https://www.isca-archive.org/interspeech_2022/boeddeker22_interspeech.pdf"}],"doi":"10.21437/interspeech.2022-10929","title":"An Initialization Scheme for Meeting Separation with Spatial Mixture Models"},{"type":"conference","publication":"Proc. Interspeech 2022","abstract":[{"text":"Recent speaker diarization studies showed that integration of end-to-end neural diarization (EEND) and clustering-based diarization is a promising approach for achieving state-of-the-art performance on various tasks. Such an approach first divides an observed signal into fixed-length segments, then performs {\\it segment-level} local diarization based on an EEND module, and merges the segment-level results via clustering to form a final global diarization result. The segmentation is done to limit the number of speakers in each segment since the current EEND cannot handle a large number of speakers. In this paper, we argue that such an approach involving the segmentation has several issues; for example, it inevitably faces a dilemma that larger segment sizes increase both the context available for enhancing the performance and the number of speakers for the local EEND module to handle. To resolve such a problem, this paper proposes a novel framework that performs diarization without segmentation. However, it can still handle challenging data containing many speakers and a significant amount of overlapping speech. The proposed method can take an entire meeting for inference and perform {\\it utterance-by-utterance} diarization that clusters utterance activities in terms of speakers. To this end, we leverage a neural network training scheme called Graph-PIT proposed recently for neural source separation. Experiments with simulated active-meeting-like data and CALLHOME data show the superiority of the proposed approach over the conventional methods.","lang":"eng"}],"status":"public","_id":"33958","user_id":"40767","department":[{"_id":"54"}],"language":[{"iso":"eng"}],"publication_status":"published","quality_controlled":"1","year":"2022","citation":{"apa":"Kinoshita, K., von Neumann, T., Delcroix, M., Boeddeker, C., &#38; Haeb-Umbach, R. (2022). Utterance-by-utterance overlap-aware neural diarization with Graph-PIT. <i>Proc. Interspeech 2022</i>, 1486–1490. <a href=\"https://doi.org/10.21437/Interspeech.2022-11408\">https://doi.org/10.21437/Interspeech.2022-11408</a>","short":"K. Kinoshita, T. von Neumann, M. Delcroix, C. Boeddeker, R. Haeb-Umbach, in: Proc. Interspeech 2022, ISCA, 2022, pp. 1486–1490.","bibtex":"@inproceedings{Kinoshita_von Neumann_Delcroix_Boeddeker_Haeb-Umbach_2022, title={Utterance-by-utterance overlap-aware neural diarization with Graph-PIT}, DOI={<a href=\"https://doi.org/10.21437/Interspeech.2022-11408\">10.21437/Interspeech.2022-11408</a>}, booktitle={Proc. Interspeech 2022}, publisher={ISCA}, author={Kinoshita, Keisuke and von Neumann, Thilo and Delcroix, Marc and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2022}, pages={1486–1490} }","mla":"Kinoshita, Keisuke, et al. “Utterance-by-Utterance Overlap-Aware Neural Diarization with Graph-PIT.” <i>Proc. Interspeech 2022</i>, ISCA, 2022, pp. 1486–90, doi:<a href=\"https://doi.org/10.21437/Interspeech.2022-11408\">10.21437/Interspeech.2022-11408</a>.","ama":"Kinoshita K, von Neumann T, Delcroix M, Boeddeker C, Haeb-Umbach R. Utterance-by-utterance overlap-aware neural diarization with Graph-PIT. In: <i>Proc. Interspeech 2022</i>. ISCA; 2022:1486-1490. doi:<a href=\"https://doi.org/10.21437/Interspeech.2022-11408\">10.21437/Interspeech.2022-11408</a>","chicago":"Kinoshita, Keisuke, Thilo von Neumann, Marc Delcroix, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Utterance-by-Utterance Overlap-Aware Neural Diarization with Graph-PIT.” In <i>Proc. Interspeech 2022</i>, 1486–90. ISCA, 2022. <a href=\"https://doi.org/10.21437/Interspeech.2022-11408\">https://doi.org/10.21437/Interspeech.2022-11408</a>.","ieee":"K. Kinoshita, T. von Neumann, M. Delcroix, C. Boeddeker, and R. Haeb-Umbach, “Utterance-by-utterance overlap-aware neural diarization with Graph-PIT,” in <i>Proc. Interspeech 2022</i>, 2022, pp. 1486–1490, doi: <a href=\"https://doi.org/10.21437/Interspeech.2022-11408\">10.21437/Interspeech.2022-11408</a>."},"page":"1486-1490","date_updated":"2025-02-12T09:09:05Z","publisher":"ISCA","author":[{"first_name":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2022-10-28T12:07:57Z","title":"Utterance-by-utterance overlap-aware neural diarization with Graph-PIT","main_file_link":[{"url":"https://www.isca-archive.org/interspeech_2022/kinoshita22_interspeech.pdf"}],"conference":{"name":"Interspeech 2022"},"doi":"10.21437/Interspeech.2022-11408"},{"file_date_updated":"2021-12-06T10:48:30Z","user_id":"49870","department":[{"_id":"54"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"26770","status":"public","type":"conference","doi":"10.21437/interspeech.2021-1177","conference":{"name":"Interspeech"},"author":[{"id":"49870","full_name":"von Neumann, Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"full_name":"Kinoshita, Keisuke","last_name":"Kinoshita","first_name":"Keisuke"},{"last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767","first_name":"Christoph"},{"first_name":"Marc","full_name":"Delcroix, Marc","last_name":"Delcroix"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"oa":"1","date_updated":"2023-11-15T12:14:40Z","citation":{"short":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Interspeech 2021, 2021.","mla":"von Neumann, Thilo, et al. “Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers.” <i>Interspeech 2021</i>, 2021, doi:<a href=\"https://doi.org/10.21437/interspeech.2021-1177\">10.21437/interspeech.2021-1177</a>.","bibtex":"@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2021, title={Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2021-1177\">10.21437/interspeech.2021-1177</a>}, booktitle={Interspeech 2021}, author={von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2021} }","apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2021). Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers. <i>Interspeech 2021</i>. Interspeech. <a href=\"https://doi.org/10.21437/interspeech.2021-1177\">https://doi.org/10.21437/interspeech.2021-1177</a>","ieee":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers,” presented at the Interspeech, 2021, doi: <a href=\"https://doi.org/10.21437/interspeech.2021-1177\">10.21437/interspeech.2021-1177</a>.","chicago":"Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach. “Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers.” In <i>Interspeech 2021</i>, 2021. <a href=\"https://doi.org/10.21437/interspeech.2021-1177\">https://doi.org/10.21437/interspeech.2021-1177</a>.","ama":"von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers. In: <i>Interspeech 2021</i>. ; 2021. doi:<a href=\"https://doi.org/10.21437/interspeech.2021-1177\">10.21437/interspeech.2021-1177</a>"},"related_material":{"link":[{"relation":"software","url":"https://github.com/fgnt/graph_pit"}]},"publication_status":"published","has_accepted_license":"1","language":[{"iso":"eng"}],"ddc":["000"],"keyword":["Continuous speech separation","automatic speech recognition","overlapped speech","permutation invariant training"],"file":[{"content_type":"video/mp4","relation":"supplementary_material","date_created":"2021-12-06T10:39:13Z","creator":"tvn","date_updated":"2021-12-06T10:48:30Z","file_id":"28327","access_level":"open_access","file_name":"Interspeech 2021 voiceover-002-compressed.mp4","file_size":9550220,"title":"Video for INTERSPEECH 2021"},{"content_type":"application/vnd.openxmlformats-officedocument.presentationml.presentation","relation":"slides","date_created":"2021-12-06T10:47:01Z","creator":"tvn","date_updated":"2021-12-06T10:47:01Z","access_level":"open_access","file_id":"28328","file_name":"Graph-PIT-poster-presentation.pptx","file_size":1337297,"title":"Slides from INTERSPEECH 2021"},{"relation":"main_file","content_type":"application/pdf","file_name":"INTERSPEECH2021_Graph_PIT.pdf","file_id":"28329","access_level":"open_access","file_size":226589,"date_created":"2021-12-06T10:48:21Z","creator":"tvn","date_updated":"2021-12-06T10:48:21Z"}],"abstract":[{"text":"Automatic transcription of meetings requires handling of overlapped speech, which calls for continuous speech separation (CSS) systems. The uPIT criterion was proposed for utterance-level separation with neural networks and introduces the constraint that the total number of speakers must not exceed the number of output channels. When processing meeting-like data in a segment-wise manner, i.e., by separating overlapping segments independently and stitching adjacent segments to continuous output streams, this constraint has to be fulfilled for any segment. In this contribution, we show that this constraint can be significantly relaxed. We propose a novel graph-based PIT criterion, which casts the assignment of utterances to output channels in a graph coloring problem. It only requires that the number of concurrently active speakers must not exceed the number of output channels. As a consequence, the system can process an arbitrary number of speakers and arbitrarily long segments and thus can handle more diverse scenarios.\r\nFurther, the stitching algorithm for obtaining a consistent output order in neighboring segments is of less importance and can even be eliminated completely, not the least reducing the computational effort. Experiments on meeting-style WSJ data show improvements in recognition performance over using the uPIT criterion. ","lang":"eng"}],"publication":"Interspeech 2021","title":"Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers","date_created":"2021-10-25T08:50:01Z","year":"2021","quality_controlled":"1"},{"file_date_updated":"2022-01-07T10:42:54Z","language":[{"iso":"eng"}],"ddc":["000"],"user_id":"49870","department":[{"_id":"54"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"29173","file":[{"relation":"poster","content_type":"application/pdf","file_name":"poster.pdf","access_level":"open_access","file_id":"29180","file_size":191938,"creator":"tvn","date_created":"2022-01-06T13:23:27Z","date_updated":"2022-01-06T13:23:27Z"},{"date_updated":"2022-01-07T10:42:54Z","creator":"tvn","date_created":"2022-01-07T10:42:54Z","file_size":236670,"file_id":"29181","access_level":"open_access","file_name":"ITG2021_Speeding_up_Permutation_Invariant_Training.pdf","content_type":"application/pdf","relation":"main_file"}],"status":"public","type":"conference","publication":"Speech Communication; 14th ITG Conference","conference":{"name":"Speech Communication; 14th ITG Conference","start_date":"2021-09-29","end_date":"2021-10-01","location":"Kiel"},"title":"Speeding Up Permutation Invariant Training for Source Separation","date_created":"2022-01-07T10:40:56Z","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","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"last_name":"Kinoshita","full_name":"Kinoshita, Keisuke","first_name":"Keisuke"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"oa":"1","date_updated":"2023-11-15T12:16:31Z","citation":{"ama":"von Neumann T, Boeddeker C, Kinoshita K, Delcroix M, Haeb-Umbach R. Speeding Up Permutation Invariant Training for Source Separation. In: <i>Speech Communication; 14th ITG Conference</i>. ; 2021.","chicago":"Neumann, Thilo von, Christoph Boeddeker, Keisuke Kinoshita, Marc Delcroix, and Reinhold Haeb-Umbach. “Speeding Up Permutation Invariant Training for Source Separation.” In <i>Speech Communication; 14th ITG Conference</i>, 2021.","ieee":"T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, and R. Haeb-Umbach, “Speeding Up Permutation Invariant Training for Source Separation,” presented at the Speech Communication; 14th ITG Conference, Kiel, 2021.","apa":"von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., &#38; Haeb-Umbach, R. (2021). Speeding Up Permutation Invariant Training for Source Separation. <i>Speech Communication; 14th ITG Conference</i>. Speech Communication; 14th ITG Conference, Kiel.","short":"T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, R. Haeb-Umbach, in: Speech Communication; 14th ITG Conference, 2021.","bibtex":"@inproceedings{von Neumann_Boeddeker_Kinoshita_Delcroix_Haeb-Umbach_2021, title={Speeding Up Permutation Invariant Training for Source Separation}, booktitle={Speech Communication; 14th ITG Conference}, author={von Neumann, Thilo and Boeddeker, Christoph and Kinoshita, Keisuke and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2021} }","mla":"von Neumann, Thilo, et al. “Speeding Up Permutation Invariant Training for Source Separation.” <i>Speech Communication; 14th ITG Conference</i>, 2021."},"year":"2021","has_accepted_license":"1","quality_controlled":"1"},{"ddc":["000"],"language":[{"iso":"eng"}],"publication":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","abstract":[{"text":"The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multispeaker speech recognition. However, up until now, state-of-theart neural network–based time domain source separation has not yet been combined with E2E speech recognition. We here demonstrate how to combine a separation module based on a Convolutional Time domain Audio Separation Network (Conv-TasNet) with an E2E speech recognizer and how to train such a model jointly by distributing it over multiple GPUs or by approximating truncated back-propagation for the convolutional front-end. To put this work into perspective and illustrate the complexity of the design space, we provide a compact overview of single-channel multi-speaker recognition systems. Our experiments show a word error rate of 11.0% on WSJ0-2mix and indicate that our joint time domain model can yield substantial improvements over cascade DNN-HMM and monolithic E2E frequency domain systems proposed so far.","lang":"eng"}],"file":[{"content_type":"application/pdf","relation":"main_file","creator":"huesera","date_created":"2020-12-16T14:09:48Z","date_updated":"2020-12-16T14:09:48Z","file_id":"20763","access_level":"open_access","file_name":"ICASSP_2020_vonNeumann_Paper.pdf","file_size":192529}],"date_created":"2020-12-16T14:07:54Z","title":"End-to-End Training of Time Domain Audio Separation and Recognition","quality_controlled":"1","year":"2020","_id":"20762","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"54"}],"user_id":"49870","file_date_updated":"2020-12-16T14:09:48Z","type":"conference","status":"public","date_updated":"2023-11-15T12:17:45Z","oa":"1","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":"Kinoshita, Keisuke","last_name":"Kinoshita","first_name":"Keisuke"},{"first_name":"Lukas","full_name":"Drude, Lukas","last_name":"Drude"},{"first_name":"Christoph","id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"first_name":"Tomohiro","last_name":"Nakatani","full_name":"Nakatani, Tomohiro"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"doi":"10.1109/ICASSP40776.2020.9053461","has_accepted_license":"1","page":"7004-7008","citation":{"apa":"von Neumann, T., Kinoshita, K., Drude, L., Boeddeker, C., Delcroix, M., Nakatani, T., &#38; Haeb-Umbach, R. (2020). End-to-End Training of Time Domain Audio Separation and Recognition. <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 7004–7008. <a href=\"https://doi.org/10.1109/ICASSP40776.2020.9053461\">https://doi.org/10.1109/ICASSP40776.2020.9053461</a>","mla":"von Neumann, Thilo, et al. “End-to-End Training of Time Domain Audio Separation and Recognition.” <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2020, pp. 7004–08, doi:<a href=\"https://doi.org/10.1109/ICASSP40776.2020.9053461\">10.1109/ICASSP40776.2020.9053461</a>.","bibtex":"@inproceedings{von Neumann_Kinoshita_Drude_Boeddeker_Delcroix_Nakatani_Haeb-Umbach_2020, title={End-to-End Training of Time Domain Audio Separation and Recognition}, DOI={<a href=\"https://doi.org/10.1109/ICASSP40776.2020.9053461\">10.1109/ICASSP40776.2020.9053461</a>}, booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={von Neumann, Thilo and Kinoshita, Keisuke and Drude, Lukas and Boeddeker, Christoph and Delcroix, Marc and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}, year={2020}, pages={7004–7008} }","short":"T. von Neumann, K. Kinoshita, L. Drude, C. Boeddeker, M. Delcroix, T. Nakatani, R. Haeb-Umbach, in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 7004–7008.","ama":"von Neumann T, Kinoshita K, Drude L, et al. End-to-End Training of Time Domain Audio Separation and Recognition. In: <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2020:7004-7008. doi:<a href=\"https://doi.org/10.1109/ICASSP40776.2020.9053461\">10.1109/ICASSP40776.2020.9053461</a>","ieee":"T. von Neumann <i>et al.</i>, “End-to-End Training of Time Domain Audio Separation and Recognition,” in <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2020, pp. 7004–7008, doi: <a href=\"https://doi.org/10.1109/ICASSP40776.2020.9053461\">10.1109/ICASSP40776.2020.9053461</a>.","chicago":"Neumann, Thilo von, Keisuke Kinoshita, Lukas Drude, Christoph Boeddeker, Marc Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “End-to-End Training of Time Domain Audio Separation and Recognition.” In <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 7004–8, 2020. <a href=\"https://doi.org/10.1109/ICASSP40776.2020.9053461\">https://doi.org/10.1109/ICASSP40776.2020.9053461</a>."}},{"page":"3097-3101","citation":{"mla":"von Neumann, Thilo, et al. “Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR.” <i>Proc. Interspeech 2020</i>, 2020, pp. 3097–101, doi:<a href=\"https://doi.org/10.21437/Interspeech.2020-2519\">10.21437/Interspeech.2020-2519</a>.","short":"T. von Neumann, C. Boeddeker, L. Drude, K. Kinoshita, M. Delcroix, T. Nakatani, R. Haeb-Umbach, in: Proc. Interspeech 2020, 2020, pp. 3097–3101.","bibtex":"@inproceedings{von Neumann_Boeddeker_Drude_Kinoshita_Delcroix_Nakatani_Haeb-Umbach_2020, title={Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR}, DOI={<a href=\"https://doi.org/10.21437/Interspeech.2020-2519\">10.21437/Interspeech.2020-2519</a>}, booktitle={Proc. Interspeech 2020}, author={von Neumann, Thilo and Boeddeker, Christoph and Drude, Lukas and Kinoshita, Keisuke and Delcroix, Marc and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}, year={2020}, pages={3097–3101} }","apa":"von Neumann, T., Boeddeker, C., Drude, L., Kinoshita, K., Delcroix, M., Nakatani, T., &#38; Haeb-Umbach, R. (2020). Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR. <i>Proc. Interspeech 2020</i>, 3097–3101. <a href=\"https://doi.org/10.21437/Interspeech.2020-2519\">https://doi.org/10.21437/Interspeech.2020-2519</a>","ama":"von Neumann T, Boeddeker C, Drude L, et al. Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR. In: <i>Proc. Interspeech 2020</i>. ; 2020:3097-3101. doi:<a href=\"https://doi.org/10.21437/Interspeech.2020-2519\">10.21437/Interspeech.2020-2519</a>","ieee":"T. von Neumann <i>et al.</i>, “Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR,” in <i>Proc. Interspeech 2020</i>, 2020, pp. 3097–3101, doi: <a href=\"https://doi.org/10.21437/Interspeech.2020-2519\">10.21437/Interspeech.2020-2519</a>.","chicago":"Neumann, Thilo von, Christoph Boeddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR.” In <i>Proc. Interspeech 2020</i>, 3097–3101, 2020. <a href=\"https://doi.org/10.21437/Interspeech.2020-2519\">https://doi.org/10.21437/Interspeech.2020-2519</a>."},"has_accepted_license":"1","doi":"10.21437/Interspeech.2020-2519","oa":"1","date_updated":"2023-11-15T12:17:57Z","author":[{"orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","full_name":"von Neumann, Thilo","id":"49870","first_name":"Thilo"},{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"first_name":"Lukas","last_name":"Drude","full_name":"Drude, Lukas"},{"full_name":"Kinoshita, Keisuke","last_name":"Kinoshita","first_name":"Keisuke"},{"last_name":"Delcroix","full_name":"Delcroix, Marc","first_name":"Marc"},{"first_name":"Tomohiro","full_name":"Nakatani, Tomohiro","last_name":"Nakatani"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"status":"public","type":"conference","file_date_updated":"2020-12-16T14:14:14Z","_id":"20764","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"54"}],"user_id":"49870","year":"2020","quality_controlled":"1","title":"Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR","date_created":"2020-12-16T14:12:45Z","abstract":[{"lang":"eng","text":"Most approaches to multi-talker overlapped speech separation and recognition assume that the number of simultaneously active speakers is given, but in realistic situations, it is typically unknown. To cope with this, we extend an iterative speech extraction system with mechanisms to count the number of sources and combine it with a single-talker speech recognizer to form the first end-to-end multi-talker automatic speech recognition system for an unknown number of active speakers. Our experiments show very promising performance in counting accuracy, source separation and speech recognition on simulated clean mixtures from WSJ0-2mix and WSJ0-3mix. Among others, we set a new state-of-the-art word error rate on the WSJ0-2mix database. Furthermore, our system generalizes well to a larger number of speakers than it ever saw during training, as shown in experiments with the WSJ0-4mix database. "}],"file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2020-12-16T14:14:14Z","creator":"huesera","date_created":"2020-12-16T14:14:14Z","file_size":267893,"file_id":"20765","file_name":"INTERSPEECH_2020_vonNeumann_Paper.pdf","access_level":"open_access"}],"publication":"Proc. Interspeech 2020","ddc":["000"],"language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"ddc":["000"],"publication":"Proc. Interspeech 2020","file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2020-12-16T14:16:32Z","creator":"huesera","date_created":"2020-12-16T14:16:32Z","file_size":1725219,"access_level":"open_access","file_name":"INTERSPEECH_2020_vonNeumann1_Paper.pdf","file_id":"20767"}],"abstract":[{"text":"Recently, the source separation performance was greatly improved by time-domain audio source separation based on dual-path recurrent neural network (DPRNN). DPRNN is a simple but effective model for a long sequential data. While DPRNN is quite efficient in modeling a sequential data of the length of an utterance, i.e., about 5 to 10 second data, it is harder to apply it to longer sequences such as whole conversations consisting of multiple utterances. It is simply because, in such a case, the number of time steps consumed by its internal module called inter-chunk RNN becomes extremely large. To mitigate this problem, this paper proposes a multi-path RNN (MPRNN), a generalized version of DPRNN, that models the input data in a hierarchical manner. In the MPRNN framework, the input data is represented at several (>_ 3) time-resolutions, each of which is modeled by a specific RNN sub-module. For example, the RNN sub-module that deals with the finest resolution may model temporal relationship only within a phoneme, while the RNN sub-module handling the most coarse resolution may capture only the relationship between utterances such as speaker information. We perform experiments using simulated dialogue-like mixtures and show that MPRNN has greater model capacity, and it outperforms the current state-of-the-art DPRNN framework especially in online processing scenarios.","lang":"eng"}],"date_created":"2020-12-16T14:15:24Z","title":"Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation","quality_controlled":"1","year":"2020","department":[{"_id":"54"}],"user_id":"49870","_id":"20766","file_date_updated":"2020-12-16T14:16:32Z","type":"conference","status":"public","author":[{"first_name":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"id":"49870","full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","first_name":"Thilo"},{"full_name":"Delcroix, Marc","last_name":"Delcroix","first_name":"Marc"},{"first_name":"Tomohiro","last_name":"Nakatani","full_name":"Nakatani, Tomohiro"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_updated":"2023-11-15T12:14:25Z","oa":"1","doi":"10.21437/Interspeech.2020-2388","has_accepted_license":"1","page":"2652-2656","citation":{"ieee":"K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, and R. Haeb-Umbach, “Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation,” in <i>Proc. Interspeech 2020</i>, 2020, pp. 2652–2656, doi: <a href=\"https://doi.org/10.21437/Interspeech.2020-2388\">10.21437/Interspeech.2020-2388</a>.","chicago":"Kinoshita, Keisuke, Thilo von Neumann, Marc Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and Its Application to Speaker Stream Separation.” In <i>Proc. Interspeech 2020</i>, 2652–56, 2020. <a href=\"https://doi.org/10.21437/Interspeech.2020-2388\">https://doi.org/10.21437/Interspeech.2020-2388</a>.","ama":"Kinoshita K, von Neumann T, Delcroix M, Nakatani T, Haeb-Umbach R. Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation. In: <i>Proc. Interspeech 2020</i>. ; 2020:2652-2656. doi:<a href=\"https://doi.org/10.21437/Interspeech.2020-2388\">10.21437/Interspeech.2020-2388</a>","apa":"Kinoshita, K., von Neumann, T., Delcroix, M., Nakatani, T., &#38; Haeb-Umbach, R. (2020). Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation. <i>Proc. Interspeech 2020</i>, 2652–2656. <a href=\"https://doi.org/10.21437/Interspeech.2020-2388\">https://doi.org/10.21437/Interspeech.2020-2388</a>","short":"K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, R. Haeb-Umbach, in: Proc. Interspeech 2020, 2020, pp. 2652–2656.","mla":"Kinoshita, Keisuke, et al. “Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and Its Application to Speaker Stream Separation.” <i>Proc. Interspeech 2020</i>, 2020, pp. 2652–56, doi:<a href=\"https://doi.org/10.21437/Interspeech.2020-2388\">10.21437/Interspeech.2020-2388</a>.","bibtex":"@inproceedings{Kinoshita_von Neumann_Delcroix_Nakatani_Haeb-Umbach_2020, title={Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation}, DOI={<a href=\"https://doi.org/10.21437/Interspeech.2020-2388\">10.21437/Interspeech.2020-2388</a>}, booktitle={Proc. Interspeech 2020}, author={Kinoshita, Keisuke and von Neumann, Thilo and Delcroix, Marc and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}, year={2020}, pages={2652–2656} }"}}]