[{"author":[{"full_name":"Ebbers, Janek","id":"34851","last_name":"Ebbers","first_name":"Janek"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"},{"full_name":"Serizel, Romain","last_name":"Serizel","first_name":"Romain"}],"date_created":"2023-11-22T08:20:26Z","date_updated":"2024-11-15T20:34:18Z","title":"Post-Processing Independent Evaluation of Sound Event Detection Systems","quality_controlled":"1","has_accepted_license":"1","page":"36–40","citation":{"chicago":"Ebbers, Janek, Reinhold Haeb-Umbach, and Romain Serizel. “Post-Processing Independent Evaluation of Sound Event Detection Systems.” In <i>Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)</i>, 36–40. Tampere, Finland, 2023.","ieee":"J. Ebbers, R. Haeb-Umbach, and R. Serizel, “Post-Processing Independent Evaluation of Sound Event Detection Systems,” in <i>Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)</i>, 2023, pp. 36–40.","ama":"Ebbers J, Haeb-Umbach R, Serizel R. Post-Processing Independent Evaluation of Sound Event Detection Systems. In: <i>Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)</i>. ; 2023:36–40.","short":"J. Ebbers, R. Haeb-Umbach, R. Serizel, in: Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023), Tampere, Finland, 2023, pp. 36–40.","bibtex":"@inproceedings{Ebbers_Haeb-Umbach_Serizel_2023, place={Tampere, Finland}, title={Post-Processing Independent Evaluation of Sound Event Detection Systems}, booktitle={Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}, year={2023}, pages={36–40} }","mla":"Ebbers, Janek, et al. “Post-Processing Independent Evaluation of Sound Event Detection Systems.” <i>Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)</i>, 2023, pp. 36–40.","apa":"Ebbers, J., Haeb-Umbach, R., &#38; Serizel, R. (2023). Post-Processing Independent Evaluation of Sound Event Detection Systems. <i>Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)</i>, 36–40."},"year":"2023","place":"Tampere, Finland","department":[{"_id":"54"}],"user_id":"34851","_id":"49111","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-22T08:25:08Z","ddc":["000"],"publication":"Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)","type":"conference","status":"public","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","file_name":"dcase2023_ebbers.pdf","file_id":"49112","access_level":"closed","file_size":221875,"date_created":"2023-11-22T08:25:08Z","creator":"ebbers","date_updated":"2023-11-22T08:25:08Z"}],"abstract":[{"text":"Due to the high variation in the application requirements of sound event detection (SED) systems, it is not sufficient to evaluate systems only in a single operating mode. Therefore, the community recently adopted the polyphonic sound detection score (PSDS) as an evaluation metric, which is the normalized area under the PSD receiver operating characteristic (PSD-ROC). It summarizes the system performance over a range of operating modes resulting from varying the decision threshold that is used to translate the system output scores into a binary detection output. Hence, it provides a more complete picture of the overall system behavior and is less biased by specific threshold tuning. However, besides the decision threshold there is also the post-processing that can be changed to enter another operating mode. In this paper we propose the post-processing independent PSDS (piPSDS) as a generalization of the PSDS. Here, the post-processing independent PSD-ROC includes operating points from varying post-processings with varying decision thresholds. Thus, it summarizes even more operating modes of an SED system and allows for system comparison without the need of implementing a post-processing and without a bias due to different post-processings. While piPSDS can in principle combine different types of post-processing, we here, as a first step, present median filter independent PSDS (miPSDS) results for this year’s DCASE Challenge Task4a systems. Source code is publicly available in our sed_scores_eval package (https://github.com/fgnt/sed_scores_eval).","lang":"eng"}]},{"language":[{"iso":"eng"}],"_id":"57098","user_id":"49871","department":[{"_id":"54"}],"status":"public","type":"conference","publication":"Proceedings of the 20th International Congress of Phonetic Sciences","title":"DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH","conference":{"name":"International Congress of Phonetic Sciences (ICPhS)","start_date":"2023-08-07","end_date":"2023-08-11","location":"Prague"},"date_updated":"2024-11-15T06:54:55Z","author":[{"full_name":"Seebauer, Fritz","last_name":"Seebauer","first_name":"Fritz"},{"first_name":"Michael","full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann"},{"first_name":"Reinhold","last_name":"Häb-Umbach","full_name":"Häb-Umbach, Reinhold","id":"242"},{"last_name":"Wagner","full_name":"Wagner, Petra","first_name":"Petra"}],"date_created":"2024-11-15T06:49:27Z","year":"2023","citation":{"ieee":"F. Seebauer, M. Kuhlmann, R. Häb-Umbach, and P. Wagner, “DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH,” presented at the International Congress of Phonetic Sciences (ICPhS), Prague, 2023.","chicago":"Seebauer, Fritz, Michael Kuhlmann, Reinhold Häb-Umbach, and Petra Wagner. “DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH.” In <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>, 2023.","ama":"Seebauer F, Kuhlmann M, Häb-Umbach R, Wagner P. DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH. In: <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>. ; 2023.","bibtex":"@inproceedings{Seebauer_Kuhlmann_Häb-Umbach_Wagner_2023, title={DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH}, booktitle={Proceedings of the 20th International Congress of Phonetic Sciences}, author={Seebauer, Fritz and Kuhlmann, Michael and Häb-Umbach, Reinhold and Wagner, Petra}, year={2023} }","short":"F. Seebauer, M. Kuhlmann, R. Häb-Umbach, P. Wagner, in: Proceedings of the 20th International Congress of Phonetic Sciences, 2023.","mla":"Seebauer, Fritz, et al. “DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH.” <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>, 2023.","apa":"Seebauer, F., Kuhlmann, M., Häb-Umbach, R., &#38; Wagner, P. (2023). DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH. <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>. International Congress of Phonetic Sciences (ICPhS), Prague."},"publication_identifier":{"isbn":["978-80-908 114-2-3"]}},{"doi":"10.1109/icassp49357.2023.10094784","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10094784"}],"author":[{"first_name":"Thilo","full_name":"von Neumann, Thilo","id":"49870","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"last_name":"Kinoshita","full_name":"Kinoshita, Keisuke","first_name":"Keisuke"},{"first_name":"Marc","last_name":"Delcroix","full_name":"Delcroix, Marc"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2025-02-12T09:16:34Z","oa":"1","citation":{"ama":"von Neumann T, Boeddeker C, Kinoshita K, Delcroix M, Haeb-Umbach R. On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. In: <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2023. doi:<a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">10.1109/icassp49357.2023.10094784</a>","chicago":"Neumann, Thilo von, Christoph Boeddeker, Keisuke Kinoshita, Marc Delcroix, and Reinhold Haeb-Umbach. “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems.” In <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2023. <a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">https://doi.org/10.1109/icassp49357.2023.10094784</a>.","ieee":"T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, and R. Haeb-Umbach, “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems,” 2023, doi: <a href=\"https://doi.org/10.1109/icassp49357.2023.10094784\">10.1109/icassp49357.2023.10094784</a>.","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} }","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>"},"related_material":{"link":[{"relation":"software","url":"https://github.com/fgnt/meeteval"}]},"has_accepted_license":"1","publication_status":"published","file_date_updated":"2023-10-19T07:41:56Z","department":[{"_id":"54"}],"user_id":"40767","_id":"48281","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"448568305","name":"Automatische Transkription von Gesprächssituationen","_id":"508"}],"status":"public","type":"conference","title":"On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems","date_created":"2023-10-19T07:38:31Z","publisher":"IEEE","year":"2023","quality_controlled":"1","language":[{"iso":"eng"}],"keyword":["Word Error Rate","Meeting Recognition","Levenshtein Distance"],"ddc":["000"],"file":[{"relation":"main_file","content_type":"application/pdf","file_size":204994,"access_level":"open_access","file_name":"ICASSP_2023_Meeting_Evaluation.pdf","file_id":"48282","date_updated":"2023-10-19T07:41:56Z","date_created":"2023-10-19T07:39:57Z","creator":"tvn"}],"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."}],"publication":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"title":"MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems","date_created":"2023-10-19T07:24:51Z","year":"2023","quality_controlled":"1","language":[{"iso":"eng"}],"keyword":["Speech Recognition","Word Error Rate","Meeting Transcription"],"ddc":["000"],"file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2023-10-19T07:19:59Z","date_created":"2023-10-19T07:19:59Z","creator":"tvn","file_size":263744,"access_level":"open_access","file_name":"Chime_7__MeetEval.pdf","file_id":"48276"}],"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","conference":{"location":"Dublin","name":"CHiME 2023 Workshop on Speech Processing in Everyday Environments"},"main_file_link":[{"url":"https://arxiv.org/abs/2307.11394","open_access":"1"}],"author":[{"first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","id":"49870","full_name":"von Neumann, Thilo"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","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"}],"oa":"1","date_updated":"2025-02-12T09:12:05Z","citation":{"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.","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} }","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.","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.","ama":"von Neumann T, Boeddeker C, Delcroix M, Haeb-Umbach R. MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. In: <i>Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments</i>. ; 2023."},"related_material":{"link":[{"url":"https://github.com/fgnt/meeteval","relation":"software"}]},"has_accepted_license":"1","file_date_updated":"2023-10-19T07:19:59Z","department":[{"_id":"54"}],"user_id":"40767","_id":"48275","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"}],"status":"public","type":"conference"},{"oa":"1","date_updated":"2025-02-12T09:14:45Z","author":[{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","first_name":"Tobias"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"full_name":"Zorilă, Cătălin","last_name":"Zorilă","first_name":"Cătălin"},{"last_name":"Doddipatla","full_name":"Doddipatla, Rama","first_name":"Rama"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"doi":"10.1109/icassp49357.2023.10095370","conference":{"location":"Rhodes","name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},"publication_status":"published","has_accepted_license":"1","citation":{"chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, and Reinhold Haeb-Umbach. “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.” In <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2023. <a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">https://doi.org/10.1109/icassp49357.2023.10095370</a>.","ieee":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, and R. Haeb-Umbach, “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization,” presented at the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, 2023, doi: <a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>.","ama":"Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. In: <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2023. doi:<a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>","mla":"Cord-Landwehr, Tobias, et al. “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.” <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2023, doi:<a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization}, DOI={<a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">10.1109/icassp49357.2023.10095370</a>}, booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2023} }","short":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023.","apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2023). Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. <i>ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes. <a href=\"https://doi.org/10.1109/icassp49357.2023.10095370\">https://doi.org/10.1109/icassp49357.2023.10095370</a>"},"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":"47128","user_id":"40767","department":[{"_id":"54"}],"file_date_updated":"2023-11-15T14:56:18Z","type":"conference","status":"public","publisher":"IEEE","date_created":"2023-09-19T14:01:20Z","title":"Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization","year":"2023","ddc":["000"],"language":[{"iso":"eng"}],"publication":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","file":[{"relation":"main_file","content_type":"application/pdf","file_id":"48932","file_name":"teacher_student_embeddings.pdf","access_level":"open_access","file_size":246306,"creator":"cord","date_created":"2023-11-15T14:56:18Z","date_updated":"2023-11-15T14:56:18Z"}]},{"_id":"47129","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"}],"department":[{"_id":"54"}],"user_id":"40767","ddc":["000"],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-15T15:00:02Z","publication":"INTERSPEECH 2023","type":"conference","status":"public","file":[{"relation":"main_file","content_type":"application/pdf","file_size":303203,"access_level":"open_access","file_name":"multispeaker_embeddings.pdf","file_id":"48933","date_updated":"2023-11-15T15:00:02Z","creator":"cord","date_created":"2023-11-15T15:00:02Z"}],"publisher":"ISCA","oa":"1","date_updated":"2025-02-12T09:15:28Z","date_created":"2023-09-19T14:34:37Z","author":[{"first_name":"Tobias","full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"first_name":"Cătălin","last_name":"Zorilă","full_name":"Zorilă, Cătălin"},{"first_name":"Rama","last_name":"Doddipatla","full_name":"Doddipatla, Rama"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"title":"A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures","doi":"10.21437/interspeech.2023-1379","has_accepted_license":"1","publication_status":"published","year":"2023","citation":{"apa":"Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., &#38; Haeb-Umbach, R. (2023). A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. <i>INTERSPEECH 2023</i>. <a href=\"https://doi.org/10.21437/interspeech.2023-1379\">https://doi.org/10.21437/interspeech.2023-1379</a>","mla":"Cord-Landwehr, Tobias, et al. “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures.” <i>INTERSPEECH 2023</i>, ISCA, 2023, doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>.","short":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.","bibtex":"@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2023} }","ama":"Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. In: <i>INTERSPEECH 2023</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Cătălin Zorilă, Rama Doddipatla, and Reinhold Haeb-Umbach. “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures.” In <i>INTERSPEECH 2023</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/interspeech.2023-1379\">https://doi.org/10.21437/interspeech.2023-1379</a>.","ieee":"T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, and R. Haeb-Umbach, “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures,” 2023, doi: <a href=\"https://doi.org/10.21437/interspeech.2023-1379\">10.21437/interspeech.2023-1379</a>."}},{"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"}],"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>.","ieee":"C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “Multi-stage diarization refinement for the CHiME-7 DASR scenario,” 2023, doi: <a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.” In <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/chime.2023-10\">https://doi.org/10.21437/chime.2023-10</a>.","ama":"Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. Multi-stage diarization refinement for the CHiME-7 DASR scenario. In: <i>7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/chime.2023-10\">10.21437/chime.2023-10</a>"},"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","date_created":"2024-05-23T15:16:15Z","author":[{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"full_name":"Cord-Landwehr, Tobias","id":"44393","last_name":"Cord-Landwehr","first_name":"Tobias"},{"last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","full_name":"von Neumann, Thilo","id":"49870","first_name":"Thilo"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}]},{"status":"public","publication":"INTERSPEECH 2023","type":"conference","language":[{"iso":"eng"}],"_id":"48390","project":[{"grant_number":"448568305","_id":"508","name":"Automatische Transkription von Gesprächssituationen"}],"department":[{"_id":"54"}],"user_id":"40767","year":"2023","citation":{"apa":"Berger, S., Vieting, P., Boeddeker, C., Schlüter, R., &#38; Haeb-Umbach, R. (2023). Mixture Encoder for Joint Speech Separation and Recognition. <i>INTERSPEECH 2023</i>. <a href=\"https://doi.org/10.21437/interspeech.2023-1815\">https://doi.org/10.21437/interspeech.2023-1815</a>","mla":"Berger, Simon, et al. “Mixture Encoder for Joint Speech Separation and Recognition.” <i>INTERSPEECH 2023</i>, ISCA, 2023, doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>.","short":"S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.","bibtex":"@inproceedings{Berger_Vieting_Boeddeker_Schlüter_Haeb-Umbach_2023, title={Mixture Encoder for Joint Speech Separation and Recognition}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Berger, Simon and Vieting, Peter and Boeddeker, Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2023} }","ama":"Berger S, Vieting P, Boeddeker C, Schlüter R, Haeb-Umbach R. Mixture Encoder for Joint Speech Separation and Recognition. In: <i>INTERSPEECH 2023</i>. ISCA; 2023. doi:<a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>","chicago":"Berger, Simon, Peter Vieting, Christoph Boeddeker, Ralf Schlüter, and Reinhold Haeb-Umbach. “Mixture Encoder for Joint Speech Separation and Recognition.” In <i>INTERSPEECH 2023</i>. ISCA, 2023. <a href=\"https://doi.org/10.21437/interspeech.2023-1815\">https://doi.org/10.21437/interspeech.2023-1815</a>.","ieee":"S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach, “Mixture Encoder for Joint Speech Separation and Recognition,” 2023, doi: <a href=\"https://doi.org/10.21437/interspeech.2023-1815\">10.21437/interspeech.2023-1815</a>."},"publication_status":"published","title":"Mixture Encoder for Joint Speech Separation and Recognition","doi":"10.21437/interspeech.2023-1815","main_file_link":[{"url":"https://www.isca-archive.org/interspeech_2023/berger23_interspeech.pdf","open_access":"1"}],"date_updated":"2025-02-12T09:11:30Z","publisher":"ISCA","oa":"1","date_created":"2023-10-23T15:06:39Z","author":[{"first_name":"Simon","last_name":"Berger","full_name":"Berger, Simon"},{"last_name":"Vieting","full_name":"Vieting, Peter","first_name":"Peter"},{"full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker","first_name":"Christoph"},{"first_name":"Ralf","last_name":"Schlüter","full_name":"Schlüter, Ralf"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}]},{"status":"public","type":"conference","publication":"Speech Communication; 15th ITG Conference","language":[{"iso":"eng"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"57086","user_id":"49871","department":[{"_id":"54"}],"year":"2023","citation":{"ama":"Kuhlmann M, Meise AT, Seebauer F, Wagner P, Häb-Umbach R. Investigating Speaker Embedding Disentanglement on Natural Read Speech. In: <i>Speech Communication; 15th ITG Conference</i>. ; 2023:121–125.","ieee":"M. Kuhlmann, A. T. Meise, F. Seebauer, P. Wagner, and R. Häb-Umbach, “Investigating Speaker Embedding Disentanglement on Natural Read Speech,” in <i>Speech Communication; 15th ITG Conference</i>, 2023, pp. 121–125.","chicago":"Kuhlmann, Michael, Adrian Tobias Meise, Fritz Seebauer, Petra Wagner, and Reinhold Häb-Umbach. “Investigating Speaker Embedding Disentanglement on Natural Read Speech.” In <i>Speech Communication; 15th ITG Conference</i>, 121–125, 2023.","bibtex":"@inproceedings{Kuhlmann_Meise_Seebauer_Wagner_Häb-Umbach_2023, title={Investigating Speaker Embedding Disentanglement on Natural Read Speech}, booktitle={Speech Communication; 15th ITG Conference}, author={Kuhlmann, Michael and Meise, Adrian Tobias and Seebauer, Fritz and Wagner, Petra and Häb-Umbach, Reinhold}, year={2023}, pages={121–125} }","short":"M. Kuhlmann, A.T. Meise, F. Seebauer, P. Wagner, R. Häb-Umbach, in: Speech Communication; 15th ITG Conference, 2023, pp. 121–125.","mla":"Kuhlmann, Michael, et al. “Investigating Speaker Embedding Disentanglement on Natural Read Speech.” <i>Speech Communication; 15th ITG Conference</i>, 2023, pp. 121–125.","apa":"Kuhlmann, M., Meise, A. T., Seebauer, F., Wagner, P., &#38; Häb-Umbach, R. (2023). Investigating Speaker Embedding Disentanglement on Natural Read Speech. <i>Speech Communication; 15th ITG Conference</i>, 121–125."},"page":"121–125","title":"Investigating Speaker Embedding Disentanglement on Natural Read Speech","date_updated":"2026-01-05T10:12:23Z","date_created":"2024-11-14T09:45:03Z","author":[{"first_name":"Michael","full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann"},{"id":"79268","full_name":"Meise, Adrian Tobias","last_name":"Meise","first_name":"Adrian Tobias"},{"first_name":"Fritz","full_name":"Seebauer, Fritz","last_name":"Seebauer"},{"first_name":"Petra","last_name":"Wagner","full_name":"Wagner, Petra"},{"id":"242","full_name":"Häb-Umbach, Reinhold","last_name":"Häb-Umbach","first_name":"Reinhold"}]},{"type":"conference","publication":"Proceedings of the 30th European Signal Processing Conference (EUSIPCO)","abstract":[{"lang":"eng","text":"The intelligibility of demodulated audio signals from analog high frequency transmissions, e.g., using single-sideband\r\n(SSB) modulation, can be severely degraded by channel distortions and/or a mismatch between modulation and demodulation carrier frequency. In this work a neural network (NN)-based approach for carrier frequency offset (CFO) estimation from demodulated SSB signals is proposed, whereby a task specific architecture is presented. Additionally, a simulation framework for SSB signals is introduced and utilized for training the NNs. The CFO estimator is combined with a speech enhancement network to investigate its influence on the enhancement performance. The NN-based system is compared to a recently proposed pitch tracking based approach on publicly available data from real high frequency transmissions. Experiments show that the NN exhibits good CFO estimation properties and results in significant improvements in speech intelligibility, especially when combined with a noise reduction network."}],"file":[{"content_type":"application/pdf","relation":"main_file","success":1,"creator":"jensheit","date_created":"2022-09-22T10:48:31Z","date_updated":"2022-09-22T10:48:31Z","file_id":"33472","access_level":"closed","file_name":"cfo.pdf","file_size":1231379}],"status":"public","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"33471","user_id":"460","department":[{"_id":"54"}],"ddc":["000"],"file_date_updated":"2022-09-22T10:48:31Z","language":[{"iso":"eng"}],"publication_status":"accepted","quality_controlled":"1","has_accepted_license":"1","place":"Belgrad","year":"2022","citation":{"ama":"Heitkämper J, Schmalenstroeer J, Haeb-Umbach R. Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels. In: <i>Proceedings of the 30th European Signal Processing Conference (EUSIPCO)</i>.","chicago":"Heitkämper, Jens, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels.” In <i>Proceedings of the 30th European Signal Processing Conference (EUSIPCO)</i>. Belgrad, n.d.","ieee":"J. Heitkämper, J. Schmalenstroeer, and R. Haeb-Umbach, “Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels,” presented at the 30th European Signal Processing Conference (EUSIPCO), Belgrad.","short":"J. Heitkämper, J. Schmalenstroeer, R. Haeb-Umbach, in: Proceedings of the 30th European Signal Processing Conference (EUSIPCO), Belgrad, n.d.","mla":"Heitkämper, Jens, et al. “Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels.” <i>Proceedings of the 30th European Signal Processing Conference (EUSIPCO)</i>.","bibtex":"@inproceedings{Heitkämper_Schmalenstroeer_Haeb-Umbach, place={Belgrad}, title={Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels}, booktitle={Proceedings of the 30th European Signal Processing Conference (EUSIPCO)}, author={Heitkämper, Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold} }","apa":"Heitkämper, J., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (n.d.). Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels. <i>Proceedings of the 30th European Signal Processing Conference (EUSIPCO)</i>. 30th European Signal Processing Conference (EUSIPCO), Belgrad."},"date_updated":"2023-10-26T08:15:57Z","author":[{"last_name":"Heitkämper","id":"27643","full_name":"Heitkämper, Jens","first_name":"Jens"},{"last_name":"Schmalenstroeer","id":"460","full_name":"Schmalenstroeer, Joerg","first_name":"Joerg"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_created":"2022-09-22T10:56:13Z","title":"Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels","conference":{"name":"30th European Signal Processing Conference (EUSIPCO)","start_date":"2022-08-29","end_date":"2022-09-02","location":"Belgrad"}},{"date_updated":"2023-11-15T14:55:14Z","oa":"1","author":[{"last_name":"Cord-Landwehr","full_name":"Cord-Landwehr, Tobias","id":"44393","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"},{"first_name":"Christoph","last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"conference":{"name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","location":"Bamberg"},"has_accepted_license":"1","citation":{"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.","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.","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.","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.","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} }","short":"T. Cord-Landwehr, T. von Neumann, C. Boeddeker, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 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."},"_id":"33847","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"54"}],"user_id":"44393","file_date_updated":"2023-11-15T14:54:56Z","type":"conference","status":"public","date_created":"2022-10-20T14:02:14Z","title":"MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator","quality_controlled":"1","year":"2022","external_id":{"arxiv":["2209.11494"]},"ddc":["000"],"language":[{"iso":"eng"}],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","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"}],"file":[{"relation":"main_file","content_type":"application/pdf","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"}]},{"title":"On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes","date_created":"2022-10-18T09:25:51Z","publisher":"IEEE","year":"2022","quality_controlled":"1","language":[{"iso":"eng"}],"ddc":["004"],"file":[{"relation":"main_file","content_type":"application/pdf","access_level":"open_access","file_name":"gburrek_icassp22.pdf","file_id":"48990","file_size":358015,"date_created":"2023-11-17T06:39:04Z","creator":"tgburrek","date_updated":"2023-11-17T06:39:04Z"}],"publication":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":"10.1109/icassp43922.2022.9746284","author":[{"first_name":"Tobias","full_name":"Gburrek, Tobias","id":"44006","last_name":"Gburrek"},{"id":"460","full_name":"Schmalenstroeer, Joerg","last_name":"Schmalenstroeer","first_name":"Joerg"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2023-11-17T06:39:28Z","oa":"1","citation":{"apa":"Gburrek, T., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2022). On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes. <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">https://doi.org/10.1109/icassp43922.2022.9746284</a>","short":"T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022.","mla":"Gburrek, Tobias, et al. “On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes.” <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/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2022, title={On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes}, DOI={<a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2022} }","ieee":"T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes,” 2022, doi: <a href=\"https://doi.org/10.1109/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes.” 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/icassp43922.2022.9746284\">https://doi.org/10.1109/icassp43922.2022.9746284</a>.","ama":"Gburrek T, Schmalenstroeer J, Haeb-Umbach R. On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes. 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/icassp43922.2022.9746284\">10.1109/icassp43922.2022.9746284</a>"},"publication_status":"published","has_accepted_license":"1","file_date_updated":"2023-11-17T06:39:04Z","user_id":"44006","department":[{"_id":"54"}],"_id":"33807","status":"public","type":"conference"},{"type":"journal_article","status":"public","department":[{"_id":"54"}],"user_id":"242","_id":"33451","file_date_updated":"2022-09-22T07:00:29Z","has_accepted_license":"1","intvolume":"        71","page":"9435-9449","citation":{"mla":"Grimm, Christopher, et al. “Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications.” <i>IEEE Transactions on Vehicular Technology</i>, vol. 71, no. 9, 2022, pp. 9435–49, doi:<a href=\"https://doi.org/10.1109/TVT.2022.3182411\">10.1109/TVT.2022.3182411</a>.","short":"C. Grimm, T. Fei, E. Warsitz, R. Farhoud, T. Breddermann, R. Haeb-Umbach, IEEE Transactions on Vehicular Technology 71 (2022) 9435–9449.","bibtex":"@article{Grimm_Fei_Warsitz_Farhoud_Breddermann_Haeb-Umbach_2022, title={Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications}, volume={71}, DOI={<a href=\"https://doi.org/10.1109/TVT.2022.3182411\">10.1109/TVT.2022.3182411</a>}, number={9}, journal={IEEE Transactions on Vehicular Technology}, author={Grimm, Christopher and Fei, Tai and Warsitz, Ernst and Farhoud, Ridha and Breddermann, Tobias and Haeb-Umbach, Reinhold}, year={2022}, pages={9435–9449} }","apa":"Grimm, C., Fei, T., Warsitz, E., Farhoud, R., Breddermann, T., &#38; Haeb-Umbach, R. (2022). Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications. <i>IEEE Transactions on Vehicular Technology</i>, <i>71</i>(9), 9435–9449. <a href=\"https://doi.org/10.1109/TVT.2022.3182411\">https://doi.org/10.1109/TVT.2022.3182411</a>","ieee":"C. Grimm, T. Fei, E. Warsitz, R. Farhoud, T. Breddermann, and R. Haeb-Umbach, “Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications,” <i>IEEE Transactions on Vehicular Technology</i>, vol. 71, no. 9, pp. 9435–9449, 2022, doi: <a href=\"https://doi.org/10.1109/TVT.2022.3182411\">10.1109/TVT.2022.3182411</a>.","chicago":"Grimm, Christopher, Tai Fei, Ernst Warsitz, Ridha Farhoud, Tobias Breddermann, and Reinhold Haeb-Umbach. “Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications.” <i>IEEE Transactions on Vehicular Technology</i> 71, no. 9 (2022): 9435–49. <a href=\"https://doi.org/10.1109/TVT.2022.3182411\">https://doi.org/10.1109/TVT.2022.3182411</a>.","ama":"Grimm C, Fei T, Warsitz E, Farhoud R, Breddermann T, Haeb-Umbach R. Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications. <i>IEEE Transactions on Vehicular Technology</i>. 2022;71(9):9435-9449. doi:<a href=\"https://doi.org/10.1109/TVT.2022.3182411\">10.1109/TVT.2022.3182411</a>"},"volume":71,"author":[{"first_name":"Christopher","last_name":"Grimm","full_name":"Grimm, Christopher"},{"first_name":"Tai","last_name":"Fei","full_name":"Fei, Tai"},{"last_name":"Warsitz","full_name":"Warsitz, Ernst","first_name":"Ernst"},{"first_name":"Ridha","last_name":"Farhoud","full_name":"Farhoud, Ridha"},{"first_name":"Tobias","last_name":"Breddermann","full_name":"Breddermann, Tobias"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"oa":"1","date_updated":"2023-11-20T16:37:16Z","doi":"10.1109/TVT.2022.3182411","publication":"IEEE Transactions on Vehicular Technology","file":[{"relation":"main_file","content_type":"application/pdf","access_level":"open_access","file_name":"T-VT_AcceptedVersion.pdf","file_id":"33460","file_size":12117870,"creator":"huesera","date_created":"2022-09-22T07:00:29Z","date_updated":"2022-09-22T07:00:29Z"}],"abstract":[{"lang":"eng","text":"We present an approach to automatically generate semantic labels for real recordings of automotive range-Doppler (RD) radar spectra. Such labels are required when training a neural network for object recognition from radar data. The automatic labeling approach rests on the simultaneous recording of camera and lidar data in addition to the radar spectrum. By warping radar spectra into the camera image, state-of-the-art object recognition algorithms can be applied to label relevant objects, such as cars, in the camera image. The warping operation is designed to be fully differentiable, which allows backpropagating the gradient computed on the camera image through the warping operation to the neural network operating on the radar data. As the warping operation relies on accurate scene flow estimation, we further propose a novel scene flow estimation algorithm which exploits information from camera, lidar and radar sensors. The\r\nproposed scene flow estimation approach is compared against a state-of-the-art scene flow algorithm, and it outperforms it by approximately 30% w.r.t. mean average error. The feasibility of the overall framework for automatic label generation for\r\nRD spectra is verified by evaluating the performance of neural networks trained with the proposed framework for Direction-of-Arrival estimation."}],"language":[{"iso":"eng"}],"ddc":["000"],"issue":"9","quality_controlled":"1","year":"2022","date_created":"2022-09-21T07:26:19Z","title":"Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications"},{"oa":"1","date_updated":"2023-11-22T13:45:30Z","author":[{"last_name":"Wiechmann","full_name":"Wiechmann, Jana","first_name":"Jana"},{"last_name":"Glarner","full_name":"Glarner, Thomas","first_name":"Thomas"},{"first_name":"Frederik","id":"72602","full_name":"Rautenberg, Frederik","last_name":"Rautenberg"},{"full_name":"Wagner, Petra","last_name":"Wagner","first_name":"Petra"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_created":"2022-10-12T07:10:03Z","title":"Technically enabled explaining of voice characteristics","conference":{"location":"Bielefeld","end_date":"2022-10-07","start_date":"2022-10-06"},"has_accepted_license":"1","year":"2022","citation":{"apa":"Wiechmann, J., Glarner, T., Rautenberg, F., Wagner, P., &#38; Haeb-Umbach, R. (2022). Technically enabled explaining of voice characteristics. <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>.","mla":"Wiechmann, Jana, et al. “Technically Enabled Explaining of Voice Characteristics.” <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>, 2022.","short":"J. Wiechmann, T. Glarner, F. Rautenberg, P. Wagner, R. Haeb-Umbach, in: 18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P), 2022.","bibtex":"@inproceedings{Wiechmann_Glarner_Rautenberg_Wagner_Haeb-Umbach_2022, title={Technically enabled explaining of voice characteristics}, booktitle={18. Phonetik und Phonologie im deutschsprachigen Raum (P&#38;P)}, author={Wiechmann, Jana and Glarner, Thomas and Rautenberg, Frederik and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022} }","ama":"Wiechmann J, Glarner T, Rautenberg F, Wagner P, Haeb-Umbach R. Technically enabled explaining of voice characteristics. In: <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>. ; 2022.","chicago":"Wiechmann, Jana, Thomas Glarner, Frederik Rautenberg, Petra Wagner, and Reinhold Haeb-Umbach. “Technically Enabled Explaining of Voice Characteristics.” In <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>, 2022.","ieee":"J. Wiechmann, T. Glarner, F. Rautenberg, P. Wagner, and R. Haeb-Umbach, “Technically enabled explaining of voice characteristics,” Bielefeld, 2022."},"_id":"33696","project":[{"name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","_id":"129","grant_number":"438445824"}],"department":[{"_id":"54"},{"_id":"660"}],"user_id":"72602","ddc":["000"],"language":[{"iso":"eng"}],"file_date_updated":"2022-10-12T07:09:26Z","publication":"18. Phonetik und Phonologie im deutschsprachigen Raum (P&P)","type":"conference","status":"public","file":[{"relation":"main_file","content_type":"application/pdf","file_id":"33697","access_level":"open_access","file_name":"PP_2022_paper_8911.pdf","file_size":109294,"creator":"huesera","date_created":"2022-10-12T07:09:26Z","date_updated":"2022-10-12T07:09:26Z"}]},{"author":[{"full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann","first_name":"Michael"},{"last_name":"Seebauer","full_name":"Seebauer, Fritz","first_name":"Fritz"},{"first_name":"Janek","last_name":"Ebbers","full_name":"Ebbers, Janek","id":"34851"},{"first_name":"Petra","last_name":"Wagner","full_name":"Wagner, Petra"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"oa":"1","date_updated":"2023-10-25T09:04:45Z","main_file_link":[{"open_access":"1","url":"https://www.isca-speech.org/archive/pdfs/interspeech_2022/kuhlmann22_interspeech.pdf"}],"doi":"10.21437/interspeech.2022-10740","publication_status":"published","has_accepted_license":"1","citation":{"ieee":"M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, and R. Haeb-Umbach, “Investigation into Target Speaking Rate Adaptation for Voice Conversion,” 2022, doi: <a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>.","chicago":"Kuhlmann, Michael, Fritz Seebauer, Janek Ebbers, Petra Wagner, and Reinhold Haeb-Umbach. “Investigation into Target Speaking Rate Adaptation for Voice Conversion.” In <i>Interspeech 2022</i>. ISCA, 2022. <a href=\"https://doi.org/10.21437/interspeech.2022-10740\">https://doi.org/10.21437/interspeech.2022-10740</a>.","ama":"Kuhlmann M, Seebauer F, Ebbers J, Wagner P, Haeb-Umbach R. Investigation into Target Speaking Rate Adaptation for Voice Conversion. In: <i>Interspeech 2022</i>. ISCA; 2022. doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>","mla":"Kuhlmann, Michael, et al. “Investigation into Target Speaking Rate Adaptation for Voice Conversion.” <i>Interspeech 2022</i>, ISCA, 2022, doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>.","bibtex":"@inproceedings{Kuhlmann_Seebauer_Ebbers_Wagner_Haeb-Umbach_2022, title={Investigation into Target Speaking Rate Adaptation for Voice Conversion}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>}, booktitle={Interspeech 2022}, publisher={ISCA}, author={Kuhlmann, Michael and Seebauer, Fritz and Ebbers, Janek and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022} }","short":"M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, R. Haeb-Umbach, in: Interspeech 2022, ISCA, 2022.","apa":"Kuhlmann, M., Seebauer, F., Ebbers, J., Wagner, P., &#38; Haeb-Umbach, R. (2022). Investigation into Target Speaking Rate Adaptation for Voice Conversion. <i>Interspeech 2022</i>. <a href=\"https://doi.org/10.21437/interspeech.2022-10740\">https://doi.org/10.21437/interspeech.2022-10740</a>"},"user_id":"34851","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"33857","file_date_updated":"2023-07-15T16:16:12Z","type":"conference","status":"public","date_created":"2022-10-21T06:50:59Z","publisher":"ISCA","title":"Investigation into Target Speaking Rate Adaptation for Voice Conversion","quality_controlled":"1","year":"2022","language":[{"iso":"eng"}],"ddc":["000"],"publication":"Interspeech 2022","file":[{"content_type":"application/pdf","relation":"main_file","success":1,"creator":"mikuhl","date_created":"2023-07-15T16:16:12Z","date_updated":"2023-07-15T16:16:12Z","file_name":"kuhlmann22_interspeech.pdf","access_level":"closed","file_id":"46070","file_size":303863}]},{"citation":{"apa":"Gburrek, T., Schmalenstroeer, J., Heitkaemper, J., &#38; Haeb-Umbach, R. (2022). Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription. <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022),  Bamberg, Germany . <a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">https://doi.org/10.1109/IWAENC53105.2022.9914772</a>","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Heitkaemper_Haeb-Umbach_2022, title={Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription}, DOI={<a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>}, booktitle={2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Heitkaemper, Jens and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. Gburrek, J. Schmalenstroeer, J. Heitkaemper, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, 2022.","mla":"Gburrek, Tobias, et al. “Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription.” <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>.","ama":"Gburrek T, Schmalenstroeer J, Heitkaemper J, Haeb-Umbach R. Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE; 2022. doi:<a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>","ieee":"T. Gburrek, J. Schmalenstroeer, J. Heitkaemper, and R. Haeb-Umbach, “Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription,” presented at the 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022),  Bamberg, Germany , 2022, doi: <a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">10.1109/IWAENC53105.2022.9914772</a>.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, Jens Heitkaemper, and Reinhold Haeb-Umbach. “Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE, 2022. <a href=\"https://doi.org/10.1109/IWAENC53105.2022.9914772\">https://doi.org/10.1109/IWAENC53105.2022.9914772</a>."},"has_accepted_license":"1","conference":{"location":" Bamberg, Germany ","end_date":"2022-09-08","start_date":"2022-09-05","name":"17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022)"},"doi":"10.1109/IWAENC53105.2022.9914772","oa":"1","date_updated":"2023-11-17T06:40:58Z","author":[{"last_name":"Gburrek","id":"44006","full_name":"Gburrek, Tobias","first_name":"Tobias"},{"last_name":"Schmalenstroeer","full_name":"Schmalenstroeer, Joerg","id":"460","first_name":"Joerg"},{"first_name":"Jens","last_name":"Heitkaemper","id":"27643","full_name":"Heitkaemper, Jens"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"status":"public","type":"conference","file_date_updated":"2023-11-17T06:40:40Z","_id":"33808","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"54"}],"user_id":"44006","year":"2022","quality_controlled":"1","title":"Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription","publisher":"IEEE","date_created":"2022-10-18T09:30:24Z","file":[{"file_id":"48991","access_level":"open_access","file_name":"iwaenc_22_camera_ready_ieee_check.pdf","file_size":266475,"creator":"tgburrek","date_created":"2023-11-17T06:40:40Z","date_updated":"2023-11-17T06:40:40Z","relation":"main_file","content_type":"application/pdf"}],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","ddc":["004"],"language":[{"iso":"eng"}]},{"publication":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","type":"conference","status":"public","file":[{"content_type":"application/pdf","relation":"main_file","creator":"ebbers","date_created":"2022-11-14T12:19:55Z","date_updated":"2022-11-14T12:19:55Z","file_id":"34073","file_name":"Template.pdf","access_level":"open_access","file_size":214001}],"abstract":[{"text":"Performing an adequate evaluation of sound event detection (SED) systems is far from trivial and is still subject to ongoing research. The recently proposed polyphonic sound detection (PSD)-receiver operating characteristic (ROC) and PSD score (PSDS) make an important step into the direction of an evaluation of SED systems which is independent from a certain decision threshold. This allows to obtain a more complete picture of the overall system behavior which is less biased by threshold tuning. Yet, the PSD-ROC is currently only approximated using a finite set of thresholds. The choice of\r\nthe thresholds used in approximation, however, can have a severe impact on the resulting PSDS. In this paper we propose a method which allows for computing system performance on an evaluation set for all possible thresholds jointly, enabling accurate computation not only of the PSD-ROC and PSDS but also of other collar-based\r\nand intersection-based performance curves. It further allows to select the threshold which best fulfills the requirements of a given application. Source code is publicly available in our SED evaluation package sed_scores_eval.","lang":"eng"}],"department":[{"_id":"54"}],"user_id":"34851","_id":"34072","language":[{"iso":"eng"}],"file_date_updated":"2022-11-14T12:19:55Z","ddc":["000"],"has_accepted_license":"1","quality_controlled":"1","citation":{"ama":"Ebbers J, Haeb-Umbach R, Serizel R. Threshold Independent Evaluation of Sound Event Detection Scores. In: <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2022.","chicago":"Ebbers, Janek, Reinhold Haeb-Umbach, and Romain Serizel. “Threshold Independent Evaluation of Sound Event Detection Scores.” In <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2022.","ieee":"J. Ebbers, R. Haeb-Umbach, and R. Serizel, “Threshold Independent Evaluation of Sound Event Detection Scores,” 2022.","short":"J. Ebbers, R. Haeb-Umbach, R. Serizel, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.","mla":"Ebbers, Janek, et al. “Threshold Independent Evaluation of Sound Event Detection Scores.” <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2022.","bibtex":"@inproceedings{Ebbers_Haeb-Umbach_Serizel_2022, title={Threshold Independent Evaluation of Sound Event Detection Scores}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}, year={2022} }","apa":"Ebbers, J., Haeb-Umbach, R., &#38; Serizel, R. (2022). Threshold Independent Evaluation of Sound Event Detection Scores. <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>."},"year":"2022","author":[{"first_name":"Janek","id":"34851","full_name":"Ebbers, Janek","last_name":"Ebbers"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"},{"first_name":"Romain","full_name":"Serizel, Romain","last_name":"Serizel"}],"date_created":"2022-11-14T12:17:03Z","oa":"1","date_updated":"2023-11-22T08:26:58Z","title":"Threshold Independent Evaluation of Sound Event Detection Scores"},{"date_updated":"2024-11-15T20:34:52Z","date_created":"2023-11-22T08:34:23Z","author":[{"id":"34851","full_name":"Ebbers, Janek","last_name":"Ebbers","first_name":"Janek"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"title":"Pre-Training And Self-Training For Sound Event Detection In Domestic Environments","has_accepted_license":"1","year":"2022","citation":{"mla":"Ebbers, Janek, and Reinhold Haeb-Umbach. <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>. 2022.","bibtex":"@book{Ebbers_Haeb-Umbach_2022, title={Pre-Training And Self-Training For Sound Event Detection In Domestic Environments}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2022} }","short":"J. Ebbers, R. Haeb-Umbach, Pre-Training And Self-Training For Sound Event Detection In Domestic Environments, 2022.","apa":"Ebbers, J., &#38; Haeb-Umbach, R. (2022). <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>.","chicago":"Ebbers, Janek, and Reinhold Haeb-Umbach. <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>, 2022.","ieee":"J. Ebbers and R. Haeb-Umbach, <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>. 2022.","ama":"Ebbers J, Haeb-Umbach R. <i>Pre-Training And Self-Training For Sound Event Detection In Domestic Environments</i>.; 2022."},"_id":"49113","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"54"}],"user_id":"34851","ddc":["000"],"language":[{"iso":"eng"}],"file_date_updated":"2023-11-22T08:35:23Z","type":"report","abstract":[{"lang":"eng","text":"In this report we present our system for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2022 Challenge Task 4: Sound Event Detection in Domestic Environments 1 . As in previous editions of the Challenge, we use forward-backward convolutional recurrent neural networks (FBCRNNs) [1, 2] for weakly labeled and semi-supervised sound event detection (SED) and eventually generate strong pseudo labels for weakly labeled and unlabeled data. Then, (tag-conditioned) bidirectional CRNNs (Bi-CRNNs) [1, 2] are trained in a strongly supervised manner as our final SED models. In each of the training stages we use multiple iterations of self-training. Compared to previous editions, we improved our system performance by 1) some tweaks regarding data augmentation, pseudo labeling and inference 2) using weakly labeled AudioSet data [3] for pretraining larger networks and 3) augmenting the DESED data [4] with strongly labeled AudioSet data [5] for finetuning of the networks. Source code is publicly available at https://github.com/fgnt/pb_sed."}],"status":"public","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","access_level":"closed","file_name":"dcase2022_tech_report_ebbers.pdf","file_id":"49114","file_size":491650,"creator":"ebbers","date_created":"2023-11-22T08:35:23Z","date_updated":"2023-11-22T08:35:23Z"}]},{"author":[{"id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr","first_name":"Tobias"},{"last_name":"Boeddeker","id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph"},{"full_name":"von Neumann, Thilo","id":"49870","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann","first_name":"Thilo"},{"full_name":"Zorila, Catalin","last_name":"Zorila","first_name":"Catalin"},{"first_name":"Rama","last_name":"Doddipatla","full_name":"Doddipatla, Rama"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"oa":"1","date_updated":"2025-02-12T09:05:25Z","conference":{"name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)"},"has_accepted_license":"1","citation":{"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.","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} }","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).","ama":"Cord-Landwehr T, Boeddeker C, von Neumann T, Zorila C, Doddipatla R, Haeb-Umbach R. Monaural source separation: From anechoic to reverberant environments. In: <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. IEEE; 2022.","ieee":"T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla, and R. Haeb-Umbach, “Monaural source separation: From anechoic to reverberant environments,” presented at the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.","chicago":"Cord-Landwehr, Tobias, Christoph Boeddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, and Reinhold Haeb-Umbach. “Monaural Source Separation: From Anechoic to Reverberant Environments.” In <i>2022 International Workshop on Acoustic Signal Enhancement (IWAENC)</i>. Bamberg: IEEE, 2022."},"place":"Bamberg","department":[{"_id":"54"}],"user_id":"40767","_id":"33848","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"}],"file_date_updated":"2023-11-15T14:52:16Z","type":"conference","status":"public","date_created":"2022-10-20T14:07:28Z","publisher":"IEEE","title":"Monaural source separation: From anechoic to reverberant environments","year":"2022","external_id":{"arxiv":["2111.07578"]},"language":[{"iso":"eng"}],"ddc":["000"],"publication":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","file":[{"file_size":212890,"file_id":"48930","file_name":"monaural_source_separation.pdf","access_level":"open_access","date_updated":"2023-11-15T14:52:16Z","date_created":"2023-11-15T14:52:16Z","creator":"cord","relation":"main_file","content_type":"application/pdf"}],"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."}]},{"department":[{"_id":"54"}],"user_id":"40767","_id":"33819","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"}],"file_date_updated":"2022-10-20T05:35:32Z","type":"conference","status":"public","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":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"last_name":"Delcroix","full_name":"Delcroix, Marc","first_name":"Marc"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"oa":"1","date_updated":"2025-02-12T09:08:14Z","doi":"10.1109/icassp43922.2022.9746757","related_material":{"link":[{"relation":"supplementary_material","url":"https://github.com/fgnt/graph_pit"}]},"has_accepted_license":"1","publication_status":"published","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>.","apa":"von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., &#38; Haeb-Umbach, R. (2022). SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">https://doi.org/10.1109/icassp43922.2022.9746757</a>","bibtex":"@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2022, title={SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}, DOI={<a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2022} }","short":"T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022.","mla":"von Neumann, Thilo, et al. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2022, doi:<a href=\"https://doi.org/10.1109/icassp43922.2022.9746757\">10.1109/icassp43922.2022.9746757</a>."},"language":[{"iso":"eng"}],"ddc":["000"],"publication":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","file":[{"relation":"main_file","content_type":"application/pdf","file_size":228069,"access_level":"open_access","file_id":"33820","file_name":"main.pdf","date_updated":"2022-10-20T05:33:10Z","date_created":"2022-10-20T05:33:10Z","creator":"tvn"},{"date_created":"2022-10-20T05:35:32Z","creator":"tvn","date_updated":"2022-10-20T05:35:32Z","file_id":"33821","access_level":"open_access","file_name":"poster.pdf","file_size":229166,"content_type":"application/pdf","relation":"poster"}],"date_created":"2022-10-20T05:29:12Z","publisher":"IEEE","title":"SA-SDR: A Novel Loss Function for Separation of Meeting Style Data","quality_controlled":"1","year":"2022"}]