[{"file_date_updated":"2022-01-07T10:42:54Z","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.","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.","short":"T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, R. Haeb-Umbach, in: Speech Communication; 14th ITG Conference, 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.","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.","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."},"quality_controlled":"1","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"oa":"1","status":"public","conference":{"location":"Kiel","start_date":"2021-09-29","name":"Speech Communication; 14th ITG Conference","end_date":"2021-10-01"},"has_accepted_license":"1","_id":"29173","ddc":["000"],"user_id":"49870","publication":"Speech Communication; 14th ITG Conference","file":[{"relation":"poster","date_updated":"2022-01-06T13:23:27Z","file_name":"poster.pdf","file_size":191938,"access_level":"open_access","file_id":"29180","content_type":"application/pdf","creator":"tvn","date_created":"2022-01-06T13:23:27Z"},{"creator":"tvn","date_created":"2022-01-07T10:42:54Z","relation":"main_file","date_updated":"2022-01-07T10:42:54Z","file_name":"ITG2021_Speeding_up_Permutation_Invariant_Training.pdf","file_size":236670,"access_level":"open_access","file_id":"29181","content_type":"application/pdf"}],"date_created":"2022-01-07T10:40:56Z","type":"conference","department":[{"_id":"54"}],"year":"2021","title":"Speeding Up Permutation Invariant Training for Source Separation","author":[{"id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo","orcid":"https://orcid.org/0000-0002-7717-8670","last_name":"von Neumann"},{"first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph","id":"40767"},{"first_name":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"last_name":"Delcroix","first_name":"Marc","full_name":"Delcroix, Marc"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2023-11-15T12:16:31Z","language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"date_updated":"2023-11-22T08:28:32Z","author":[{"id":"34851","last_name":"Ebbers","first_name":"Janek","full_name":"Ebbers, Janek"},{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"}],"publication_identifier":{"isbn":["978-84-09-36072-7"]},"title":"Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments","year":"2021","department":[{"_id":"54"}],"type":"conference","date_created":"2022-01-13T08:07:47Z","file":[{"date_created":"2022-01-13T08:08:54Z","creator":"ebbers","file_id":"29309","content_type":"application/pdf","relation":"main_file","date_updated":"2022-01-13T08:19:50Z","file_name":"template.pdf","file_size":239462,"access_level":"open_access"}],"abstract":[{"text":"In this paper we present our system for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2021 Challenge Task 4: Sound Event Detection and Separation in Domestic Environments, where it scored the fourth rank. Our presented solution is an advancement of our system used in the previous edition of the task.We use a forward-backward convolutional recurrent neural network (FBCRNN) for tagging and pseudo labeling followed by tag-conditioned sound event detection (SED) models which are trained using strong pseudo labels provided by the FBCRNN. Our advancement over our earlier model is threefold. First, we introduce a strong label loss in the objective of the FBCRNN to take advantage of the strongly labeled synthetic data during training. Second, we perform multiple iterations of self-training for both the FBCRNN and tag-conditioned SED models. Third, while we used only tag-conditioned CNNs as our SED model in the previous edition we here explore sophisticated tag-conditioned SED model architectures, namely, bidirectional CRNNs and bidirectional convolutional transformer neural networks (CTNNs), and combine them. With metric and class specific tuning of median filter lengths for post-processing, our final SED model, consisting of 6 submodels (2 of each architecture), achieves on the public evaluation set poly-phonic sound event detection scores (PSDS) of 0.455 for scenario 1 and 0.684 for scenario as well as a collar-based F1-score of 0.596 outperforming the baselines and our model from the previous edition by far. Source code is publicly available at https://github.com/fgnt/pb_sed.","lang":"eng"}],"publication":"Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)","ddc":["000"],"user_id":"34851","_id":"29308","page":"226–230","has_accepted_license":"1","status":"public","oa":"1","place":"Barcelona, Spain","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"quality_controlled":"1","citation":{"short":"J. Ebbers, R. Haeb-Umbach, in: Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021), Barcelona, Spain, 2021, pp. 226–230.","chicago":"Ebbers, Janek, and Reinhold Haeb-Umbach. “Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments.” In <i>Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)</i>, 226–230. Barcelona, Spain, 2021.","ieee":"J. Ebbers and R. Haeb-Umbach, “Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments,” in <i>Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)</i>, 2021, pp. 226–230.","apa":"Ebbers, J., &#38; Haeb-Umbach, R. (2021). Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments. <i>Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)</i>, 226–230.","bibtex":"@inproceedings{Ebbers_Haeb-Umbach_2021, place={Barcelona, Spain}, title={Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments}, booktitle={Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2021}, pages={226–230} }","ama":"Ebbers J, Haeb-Umbach R. Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments. In: <i>Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)</i>. ; 2021:226–230.","mla":"Ebbers, Janek, and Reinhold Haeb-Umbach. “Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments.” <i>Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)</i>, 2021, pp. 226–230."},"file_date_updated":"2022-01-13T08:19:50Z"},{"ddc":["000"],"user_id":"34851","page":"1135–1139","_id":"29306","has_accepted_license":"1","status":"public","oa":"1","quality_controlled":"1","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"file_date_updated":"2022-01-13T08:19:35Z","citation":{"mla":"Ebbers, Janek, et al. “Adapting Sound Recognition to A New Environment Via Self-Training.” <i>Proceedings of the 29th European Signal Processing Conference (EUSIPCO)</i>, 2021, pp. 1135–1139.","bibtex":"@inproceedings{Ebbers_Keyser_Haeb-Umbach_2021, title={Adapting Sound Recognition to A New Environment Via Self-Training}, booktitle={Proceedings of the 29th European Signal Processing Conference (EUSIPCO)}, author={Ebbers, Janek and Keyser, Moritz Curt and Haeb-Umbach, Reinhold}, year={2021}, pages={1135–1139} }","ama":"Ebbers J, Keyser MC, Haeb-Umbach R. Adapting Sound Recognition to A New Environment Via Self-Training. In: <i>Proceedings of the 29th European Signal Processing Conference (EUSIPCO)</i>. ; 2021:1135–1139.","ieee":"J. Ebbers, M. C. Keyser, and R. Haeb-Umbach, “Adapting Sound Recognition to A New Environment Via Self-Training,” in <i>Proceedings of the 29th European Signal Processing Conference (EUSIPCO)</i>, 2021, pp. 1135–1139.","apa":"Ebbers, J., Keyser, M. C., &#38; Haeb-Umbach, R. (2021). Adapting Sound Recognition to A New Environment Via Self-Training. <i>Proceedings of the 29th European Signal Processing Conference (EUSIPCO)</i>, 1135–1139.","chicago":"Ebbers, Janek, Moritz Curt Keyser, and Reinhold Haeb-Umbach. “Adapting Sound Recognition to A New Environment Via Self-Training.” In <i>Proceedings of the 29th European Signal Processing Conference (EUSIPCO)</i>, 1135–1139, 2021.","short":"J. Ebbers, M.C. Keyser, R. Haeb-Umbach, in: Proceedings of the 29th European Signal Processing Conference (EUSIPCO), 2021, pp. 1135–1139."},"language":[{"iso":"eng"}],"date_updated":"2023-11-22T08:28:50Z","year":"2021","title":"Adapting Sound Recognition to A New Environment Via Self-Training","author":[{"full_name":"Ebbers, Janek","first_name":"Janek","last_name":"Ebbers","id":"34851"},{"full_name":"Keyser, Moritz Curt","first_name":"Moritz Curt","last_name":"Keyser"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"type":"conference","department":[{"_id":"54"}],"file":[{"date_updated":"2022-01-13T08:19:35Z","relation":"main_file","access_level":"open_access","file_size":213938,"file_name":"conference_101719.pdf","content_type":"application/pdf","file_id":"29307","creator":"ebbers","date_created":"2022-01-13T08:03:26Z"}],"date_created":"2022-01-13T08:01:21Z","abstract":[{"text":"Recently, there has been a rising interest in sound recognition via Acoustic Sensor Networks to support applications such as ambient assisted living or environmental habitat monitoring. With state-of-the-art sound recognition being dominated by deep-learning-based approaches, there is a high demand for labeled training data. Despite the availability of large-scale  data sets such as Google's AudioSet, acquiring training data matching a certain application environment is still often a problem. In this paper we are concerned with human activity monitoring in a domestic environment using an ASN consisting of multiple nodes each providing multichannel signals. We propose a self-training based domain adaptation approach, which only requires unlabeled data from the target environment. Here, a sound recognition system trained on AudioSet, the teacher, generates pseudo labels for data from the target environment on which a student network is trained. The student can furthermore glean information about the spatial arrangement of sensors and sound sources to further improve classification performance. It is shown that  the student significantly improves recognition performance over the pre-trained teacher without relying on labeled data from the environment the system is deployed in.","lang":"eng"}],"publication":"Proceedings of the 29th European Signal Processing Conference (EUSIPCO)"},{"department":[{"_id":"603"},{"_id":"749"},{"_id":"424"},{"_id":"67"},{"_id":"574"},{"_id":"184"},{"_id":"757"},{"_id":"54"},{"_id":"178"}],"type":"journal_article","keyword":["Explainability","process ofexplaining andunderstanding","explainable artificial systems"],"date_created":"2021-09-14T20:52:57Z","file":[{"creator":"haebumb","date_created":"2023-11-20T16:33:51Z","access_level":"open_access","file_size":626217,"file_name":"2020-12-01_explainability_final_version.pdf","date_updated":"2023-11-20T16:33:51Z","relation":"main_file","content_type":"application/pdf","file_id":"49081"}],"abstract":[{"text":"One objective of current research in explainable intelligent systems is to implement social aspects in order to increase the relevance of explanations. In this paper, we argue that a novel conceptual framework is needed to overcome shortcomings of existing AI systems with little attention to processes of interaction and learning. Drawing from research in interaction and development, we first outline the novel conceptual framework that pushes the design of AI systems toward true interactivity with an emphasis on the role of the partner and social relevance. We propose that AI systems will be able to provide a meaningful and relevant explanation only if the process of explaining is extended to active contribution of both partners that brings about dynamics that is modulated by different levels of analysis. Accordingly, our conceptual framework comprises monitoring and scaffolding as key concepts and claims that the process of explaining is not only modulated by the interaction between explainee and explainer but is embedded into a larger social context in which conventionalized and routinized behaviors are established. We discuss our conceptual framework in relation to the established objectives of transparency and autonomy that are raised for the design of explainable AI systems currently.","lang":"eng"}],"publication":"IEEE Transactions on Cognitive and Developmental Systems","issue":"3","doi":"10.1109/tcds.2020.3044366","language":[{"iso":"eng"}],"article_type":"original","intvolume":"        13","publication_status":"published","date_updated":"2023-12-05T10:15:02Z","author":[{"id":"50352","full_name":"Rohlfing, Katharina J.","first_name":"Katharina J.","last_name":"Rohlfing"},{"last_name":"Cimiano","first_name":"Philipp","full_name":"Cimiano, Philipp"},{"id":"451","last_name":"Scharlau","first_name":"Ingrid","orcid":"0000-0003-2364-9489","full_name":"Scharlau, Ingrid"},{"id":"65695","full_name":"Matzner, Tobias","first_name":"Tobias","last_name":"Matzner"},{"full_name":"Buhl, Heike M.","first_name":"Heike M.","last_name":"Buhl","id":"27152"},{"first_name":"Hendrik","last_name":"Buschmeier","full_name":"Buschmeier, Hendrik"},{"last_name":"Esposito","first_name":"Elena","full_name":"Esposito, Elena"},{"id":"57578","last_name":"Grimminger","first_name":"Angela","full_name":"Grimminger, Angela"},{"full_name":"Hammer, Barbara","first_name":"Barbara","last_name":"Hammer"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"},{"id":"68836","full_name":"Horwath, Ilona","last_name":"Horwath","first_name":"Ilona"},{"id":"48129","first_name":"Eyke","last_name":"Hüllermeier","full_name":"Hüllermeier, Eyke"},{"first_name":"Friederike","last_name":"Kern","full_name":"Kern, Friederike"},{"full_name":"Kopp, Stefan","last_name":"Kopp","first_name":"Stefan"},{"full_name":"Thommes, Kirsten","first_name":"Kirsten","last_name":"Thommes","id":"72497"},{"id":"65716","full_name":"Ngonga Ngomo, Axel-Cyrille","first_name":"Axel-Cyrille","last_name":"Ngonga Ngomo"},{"id":"60311","full_name":"Schulte, Carsten","last_name":"Schulte","first_name":"Carsten"},{"id":"3900","full_name":"Wachsmuth, Henning","first_name":"Henning","last_name":"Wachsmuth"},{"last_name":"Wagner","first_name":"Petra","full_name":"Wagner, Petra"},{"first_name":"Britta","last_name":"Wrede","full_name":"Wrede, Britta"}],"publication_identifier":{"issn":["2379-8920","2379-8939"]},"year":"2021","title":"Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems","oa":"1","project":[{"name":"TRR 318: TRR 318 - Erklärbarkeit konstruieren","grant_number":"438445824","_id":"109"}],"quality_controlled":"1","citation":{"chicago":"Rohlfing, Katharina J., Philipp Cimiano, Ingrid Scharlau, Tobias Matzner, Heike M. Buhl, Hendrik Buschmeier, Elena Esposito, et al. “Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems.” <i>IEEE Transactions on Cognitive and Developmental Systems</i> 13, no. 3 (2021): 717–28. <a href=\"https://doi.org/10.1109/tcds.2020.3044366\">https://doi.org/10.1109/tcds.2020.3044366</a>.","short":"K.J. Rohlfing, P. Cimiano, I. Scharlau, T. Matzner, H.M. Buhl, H. Buschmeier, E. Esposito, A. Grimminger, B. Hammer, R. Haeb-Umbach, I. Horwath, E. Hüllermeier, F. Kern, S. Kopp, K. Thommes, A.-C. Ngonga Ngomo, C. Schulte, H. Wachsmuth, P. Wagner, B. Wrede, IEEE Transactions on Cognitive and Developmental Systems 13 (2021) 717–728.","apa":"Rohlfing, K. J., Cimiano, P., Scharlau, I., Matzner, T., Buhl, H. M., Buschmeier, H., Esposito, E., Grimminger, A., Hammer, B., Haeb-Umbach, R., Horwath, I., Hüllermeier, E., Kern, F., Kopp, S., Thommes, K., Ngonga Ngomo, A.-C., Schulte, C., Wachsmuth, H., Wagner, P., &#38; Wrede, B. (2021). Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems. <i>IEEE Transactions on Cognitive and Developmental Systems</i>, <i>13</i>(3), 717–728. <a href=\"https://doi.org/10.1109/tcds.2020.3044366\">https://doi.org/10.1109/tcds.2020.3044366</a>","ieee":"K. J. Rohlfing <i>et al.</i>, “Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems,” <i>IEEE Transactions on Cognitive and Developmental Systems</i>, vol. 13, no. 3, pp. 717–728, 2021, doi: <a href=\"https://doi.org/10.1109/tcds.2020.3044366\">10.1109/tcds.2020.3044366</a>.","ama":"Rohlfing KJ, Cimiano P, Scharlau I, et al. Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems. <i>IEEE Transactions on Cognitive and Developmental Systems</i>. 2021;13(3):717-728. doi:<a href=\"https://doi.org/10.1109/tcds.2020.3044366\">10.1109/tcds.2020.3044366</a>","bibtex":"@article{Rohlfing_Cimiano_Scharlau_Matzner_Buhl_Buschmeier_Esposito_Grimminger_Hammer_Haeb-Umbach_et al._2021, title={Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems}, volume={13}, DOI={<a href=\"https://doi.org/10.1109/tcds.2020.3044366\">10.1109/tcds.2020.3044366</a>}, number={3}, journal={IEEE Transactions on Cognitive and Developmental Systems}, author={Rohlfing, Katharina J. and Cimiano, Philipp and Scharlau, Ingrid and Matzner, Tobias and Buhl, Heike M. and Buschmeier, Hendrik and Esposito, Elena and Grimminger, Angela and Hammer, Barbara and Haeb-Umbach, Reinhold and et al.}, year={2021}, pages={717–728} }","mla":"Rohlfing, Katharina J., et al. “Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems.” <i>IEEE Transactions on Cognitive and Developmental Systems</i>, vol. 13, no. 3, 2021, pp. 717–28, doi:<a href=\"https://doi.org/10.1109/tcds.2020.3044366\">10.1109/tcds.2020.3044366</a>."},"file_date_updated":"2023-11-20T16:33:51Z","volume":13,"user_id":"42933","ddc":["300"],"_id":"24456","page":"717-728","has_accepted_license":"1","status":"public"},{"citation":{"mla":"Haeb-Umbach, Reinhold. “Sprachtechnologien Für Digitale Assistenten.” <i>Studientexte Zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020</i>, edited by Ronald Böck et al., TUDpress, Dresden, 2020, pp. 227–34.","ama":"Haeb-Umbach R. Sprachtechnologien für Digitale Assistenten. In: Böck R, Siegert I, Wendemuth A, eds. <i>Studientexte Zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020</i>. TUDpress, Dresden; 2020:227-234.","bibtex":"@inproceedings{Haeb-Umbach_2020, title={Sprachtechnologien für Digitale Assistenten}, booktitle={Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020}, publisher={TUDpress, Dresden}, author={Haeb-Umbach, Reinhold}, editor={Böck, Ronald and Siegert, Ingo and Wendemuth, AndreasEditors}, year={2020}, pages={227–234} }","apa":"Haeb-Umbach, R. (2020). Sprachtechnologien für Digitale Assistenten. In R. Böck, I. Siegert, &#38; A. Wendemuth (Eds.), <i>Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020</i> (pp. 227–234). TUDpress, Dresden.","ieee":"R. Haeb-Umbach, “Sprachtechnologien für Digitale Assistenten,” in <i>Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020</i>, 2020, pp. 227–234.","short":"R. Haeb-Umbach, in: R. Böck, I. Siegert, A. Wendemuth (Eds.), Studientexte Zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020, TUDpress, Dresden, 2020, pp. 227–234.","chicago":"Haeb-Umbach, Reinhold. “Sprachtechnologien Für Digitale Assistenten.” In <i>Studientexte Zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020</i>, edited by Ronald Böck, Ingo Siegert, and Andreas Wendemuth, 227–34. TUDpress, Dresden, 2020."},"publication":"Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2020","date_created":"2020-08-10T09:53:12Z","department":[{"_id":"54"}],"oa":"1","type":"conference","keyword":["Poster"],"publication_identifier":{"isbn":["978-3-959081-93-1"]},"author":[{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"}],"title":"Sprachtechnologien für Digitale Assistenten","year":"2020","status":"public","date_updated":"2022-01-06T06:53:19Z","_id":"17763","language":[{"iso":"eng"}],"publisher":"TUDpress, Dresden","page":"227-234","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2020/ESSV_2020_haeb_umbach.pdf","open_access":"1"}],"editor":[{"full_name":"Böck, Ronald","last_name":"Böck","first_name":"Ronald"},{"full_name":"Siegert, Ingo","last_name":"Siegert","first_name":"Ingo"},{"first_name":"Andreas","last_name":"Wendemuth","full_name":"Wendemuth, Andreas"}],"user_id":"44006"},{"citation":{"mla":"Boeddeker, Christoph, et al. “Towards a Speaker Diarization System for the CHiME 2020 Dinner Party Transcription.” <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>, 2020.","bibtex":"@inproceedings{Boeddeker_Cord-Landwehr_Heitkaemper_Zorila_Hayakawa_Li_Liu_Doddipatla_Haeb-Umbach_2020, title={Towards a speaker diarization system for the CHiME 2020 dinner party transcription}, booktitle={Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and Heitkaemper, Jens and Zorila, Catalin and Hayakawa, Daichi and Li, Mohan and Liu, Min and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2020} }","ama":"Boeddeker C, Cord-Landwehr T, Heitkaemper J, et al. Towards a speaker diarization system for the CHiME 2020 dinner party transcription. In: <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>. ; 2020.","ieee":"C. Boeddeker <i>et al.</i>, “Towards a speaker diarization system for the CHiME 2020 dinner party transcription,” in <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>, 2020.","apa":"Boeddeker, C., Cord-Landwehr, T., Heitkaemper, J., Zorila, C., Hayakawa, D., Li, M., … Haeb-Umbach, R. (2020). Towards a speaker diarization system for the CHiME 2020 dinner party transcription. In <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>.","chicago":"Boeddeker, Christoph, Tobias Cord-Landwehr, Jens Heitkaemper, Catalin Zorila, Daichi Hayakawa, Mohan Li, Min Liu, Rama Doddipatla, and Reinhold Haeb-Umbach. “Towards a Speaker Diarization System for the CHiME 2020 Dinner Party Transcription.” In <i>Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments</i>, 2020.","short":"C. Boeddeker, T. Cord-Landwehr, J. Heitkaemper, C. Zorila, D. Hayakawa, M. Li, M. Liu, R. Doddipatla, R. Haeb-Umbach, in: Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments, 2020."},"file_date_updated":"2020-12-11T12:48:48Z","publication":"Proc. CHiME 2020 Workshop on Speech Processing in Everyday Environments","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2020-12-11T12:49:13Z","file":[{"creator":"cbj","date_created":"2020-12-11T12:48:48Z","date_updated":"2020-12-11T12:48:48Z","relation":"main_file","file_size":115421,"access_level":"open_access","file_name":"template.pdf","content_type":"application/pdf","file_id":"20702"}],"department":[{"_id":"54"}],"oa":"1","type":"conference","author":[{"id":"40767","full_name":"Boeddeker, Christoph","first_name":"Christoph","last_name":"Boeddeker"},{"id":"44393","full_name":"Cord-Landwehr, Tobias","first_name":"Tobias","last_name":"Cord-Landwehr"},{"id":"27643","last_name":"Heitkaemper","first_name":"Jens","full_name":"Heitkaemper, Jens"},{"last_name":"Zorila","first_name":"Catalin","full_name":"Zorila, Catalin"},{"first_name":"Daichi","last_name":"Hayakawa","full_name":"Hayakawa, Daichi"},{"first_name":"Mohan","last_name":"Li","full_name":"Li, Mohan"},{"full_name":"Liu, Min","last_name":"Liu","first_name":"Min"},{"full_name":"Doddipatla, Rama","last_name":"Doddipatla","first_name":"Rama"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"status":"public","title":"Towards a speaker diarization system for the CHiME 2020 dinner party transcription","year":"2020","has_accepted_license":"1","date_updated":"2022-01-06T06:54:33Z","_id":"20700","language":[{"iso":"eng"}],"user_id":"40767","ddc":["000"]},{"publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","citation":{"ama":"Nakatani T, Boeddeker C, Kinoshita K, Ikeshita R, Delcroix M, Haeb-Umbach R. Jointly optimal denoising, dereverberation, and source separation. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>. Published online 2020:1-1. doi:<a href=\"https://doi.org/10.1109/TASLP.2020.3013118\">10.1109/TASLP.2020.3013118</a>","bibtex":"@article{Nakatani_Boeddeker_Kinoshita_Ikeshita_Delcroix_Haeb-Umbach_2020, title={Jointly optimal denoising, dereverberation, and source separation}, DOI={<a href=\"https://doi.org/10.1109/TASLP.2020.3013118\">10.1109/TASLP.2020.3013118</a>}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, author={Nakatani, Tomohiro and Boeddeker, Christoph and Kinoshita, Keisuke and Ikeshita, Rintaro and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2020}, pages={1–1} }","mla":"Nakatani, Tomohiro, et al. “Jointly Optimal Denoising, Dereverberation, and Source Separation.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, 2020, pp. 1–1, doi:<a href=\"https://doi.org/10.1109/TASLP.2020.3013118\">10.1109/TASLP.2020.3013118</a>.","short":"T. Nakatani, C. Boeddeker, K. Kinoshita, R. Ikeshita, M. Delcroix, R. Haeb-Umbach, IEEE/ACM Transactions on Audio, Speech, and Language Processing (2020) 1–1.","chicago":"Nakatani, Tomohiro, Christoph Boeddeker, Keisuke Kinoshita, Rintaro Ikeshita, Marc Delcroix, and Reinhold Haeb-Umbach. “Jointly Optimal Denoising, Dereverberation, and Source Separation.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, 2020, 1–1. <a href=\"https://doi.org/10.1109/TASLP.2020.3013118\">https://doi.org/10.1109/TASLP.2020.3013118</a>.","apa":"Nakatani, T., Boeddeker, C., Kinoshita, K., Ikeshita, R., Delcroix, M., &#38; Haeb-Umbach, R. (2020). Jointly optimal denoising, dereverberation, and source separation. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, 1–1. <a href=\"https://doi.org/10.1109/TASLP.2020.3013118\">https://doi.org/10.1109/TASLP.2020.3013118</a>","ieee":"T. Nakatani, C. Boeddeker, K. Kinoshita, R. Ikeshita, M. Delcroix, and R. Haeb-Umbach, “Jointly optimal denoising, dereverberation, and source separation,” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, pp. 1–1, 2020, doi: <a href=\"https://doi.org/10.1109/TASLP.2020.3013118\">10.1109/TASLP.2020.3013118</a>."},"type":"journal_article","department":[{"_id":"54"}],"oa":"1","date_created":"2020-08-05T06:16:56Z","date_updated":"2022-12-05T12:34:01Z","status":"public","title":"Jointly optimal denoising, dereverberation, and source separation","year":"2020","author":[{"full_name":"Nakatani, Tomohiro","last_name":"Nakatani","first_name":"Tomohiro"},{"id":"40767","last_name":"Boeddeker","first_name":"Christoph","full_name":"Boeddeker, Christoph"},{"full_name":"Kinoshita, Keisuke","first_name":"Keisuke","last_name":"Kinoshita"},{"last_name":"Ikeshita","first_name":"Rintaro","full_name":"Ikeshita, Rintaro"},{"full_name":"Delcroix, Marc","first_name":"Marc","last_name":"Delcroix"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold","id":"242"}],"user_id":"40767","doi":"10.1109/TASLP.2020.3013118","page":"1-1","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2020/journal_2020_boeddeker.pdf","open_access":"1"}],"language":[{"iso":"eng"}],"_id":"17598"},{"language":[{"iso":"eng"}],"year":"2020","title":"Demystifying TasNet: A Dissecting Approach","author":[{"id":"27643","full_name":"Heitkaemper, Jens","last_name":"Heitkaemper","first_name":"Jens"},{"full_name":"Jakobeit, Darius","first_name":"Darius","last_name":"Jakobeit"},{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"full_name":"Drude, Lukas","first_name":"Lukas","last_name":"Drude"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2022-01-13T08:47:32Z","file":[{"file_id":"20699","success":1,"content_type":"application/pdf","relation":"main_file","date_updated":"2020-12-11T12:36:37Z","file_name":"ms.pdf","access_level":"closed","file_size":3871374,"date_created":"2020-12-11T12:36:37Z","creator":"jensheit"}],"date_created":"2020-11-25T14:56:53Z","keyword":["voice activity detection","speech activity detection","neural network","statistical speech processing"],"type":"conference","department":[{"_id":"54"}],"publication":"ICASSP 2020 Virtual Barcelona Spain","abstract":[{"text":"In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments. In this paper we dissect the gains of the time-domain audio separation network (TasNet) approach by gradually replacing components of an utterance-level permutation invariant training (u-PIT) based separation system in the frequency domain until the TasNet system is reached, thus blending components of frequency domain approaches with those of time domain approaches. Some of the intermediate variants achieve comparable signal-to-distortion ratio (SDR) gains to TasNet, but retain the advantage of frequency domain processing: compatibility with classic signal processing tools such as frequency-domain beamforming and the human interpretability of the masks. Furthermore, we show that the scale invariant signal-to-distortion ratio (si-SDR) criterion used as loss function in TasNet is related to a logarithmic mean square error criterion and that it is this criterion which contributes most reliable to the performance advantage of TasNet. Finally, we critically assess which gains in a noise-free single channel environment generalize to more realistic reverberant conditions.","lang":"eng"}],"_id":"20504","ddc":["000"],"user_id":"40767","status":"public","has_accepted_license":"1","file_date_updated":"2020-12-11T12:36:37Z","citation":{"mla":"Heitkaemper, Jens, et al. “Demystifying TasNet: A Dissecting Approach.” <i>ICASSP 2020 Virtual Barcelona Spain</i>, 2020.","bibtex":"@inproceedings{Heitkaemper_Jakobeit_Boeddeker_Drude_Haeb-Umbach_2020, title={Demystifying TasNet: A Dissecting Approach}, booktitle={ICASSP 2020 Virtual Barcelona Spain}, author={Heitkaemper, Jens and Jakobeit, Darius and Boeddeker, Christoph and Drude, Lukas and Haeb-Umbach, Reinhold}, year={2020} }","ama":"Heitkaemper J, Jakobeit D, Boeddeker C, Drude L, Haeb-Umbach R. Demystifying TasNet: A Dissecting Approach. In: <i>ICASSP 2020 Virtual Barcelona Spain</i>. ; 2020.","ieee":"J. Heitkaemper, D. Jakobeit, C. Boeddeker, L. Drude, and R. Haeb-Umbach, “Demystifying TasNet: A Dissecting Approach,” 2020.","apa":"Heitkaemper, J., Jakobeit, D., Boeddeker, C., Drude, L., &#38; Haeb-Umbach, R. (2020). Demystifying TasNet: A Dissecting Approach. <i>ICASSP 2020 Virtual Barcelona Spain</i>.","short":"J. Heitkaemper, D. Jakobeit, C. Boeddeker, L. Drude, R. Haeb-Umbach, in: ICASSP 2020 Virtual Barcelona Spain, 2020.","chicago":"Heitkaemper, Jens, Darius Jakobeit, Christoph Boeddeker, Lukas Drude, and Reinhold Haeb-Umbach. “Demystifying TasNet: A Dissecting Approach.” In <i>ICASSP 2020 Virtual Barcelona Spain</i>, 2020."},"quality_controlled":"1","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}]},{"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"citation":{"ama":"Heitkaemper J, Schmalenstroeer J, Haeb-Umbach R. Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments. In: <i>INTERSPEECH 2020 Virtual Shanghai China</i>. ; 2020.","bibtex":"@inproceedings{Heitkaemper_Schmalenstroeer_Haeb-Umbach_2020, title={Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments}, booktitle={INTERSPEECH 2020 Virtual Shanghai China}, author={Heitkaemper, Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2020} }","mla":"Heitkaemper, Jens, et al. “Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments.” <i>INTERSPEECH 2020 Virtual Shanghai China</i>, 2020.","chicago":"Heitkaemper, Jens, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments.” In <i>INTERSPEECH 2020 Virtual Shanghai China</i>, 2020.","short":"J. Heitkaemper, J. Schmalenstroeer, R. Haeb-Umbach, in: INTERSPEECH 2020 Virtual Shanghai China, 2020.","apa":"Heitkaemper, J., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2020). Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments. <i>INTERSPEECH 2020 Virtual Shanghai China</i>.","ieee":"J. Heitkaemper, J. Schmalenstroeer, and R. Haeb-Umbach, “Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments,” 2020."},"file_date_updated":"2020-12-11T12:33:04Z","has_accepted_license":"1","status":"public","user_id":"460","ddc":["000"],"_id":"20505","abstract":[{"lang":"eng","text":"Speech activity detection (SAD), which often rests on the fact that the noise is \"more'' stationary than speech, is particularly challenging in non-stationary environments, because the time variance of the acoustic scene makes it difficult to discriminate  speech from noise. We propose two approaches to SAD, where one is based on statistical signal processing, while the other utilizes neural networks. The former employs sophisticated signal processing to track the noise and speech energies and is meant to support the case for a resource efficient, unsupervised signal processing approach.\r\nThe latter introduces a recurrent network layer that operates on short segments of the input speech to do temporal smoothing in the presence of non-stationary noise. The systems are tested on the Fearless Steps challenge database, which consists of the transmission data from the Apollo-11 space mission.\r\nThe statistical SAD  achieves comparable detection performance to earlier proposed neural network based SADs, while the neural network based approach leads to a decision cost function of 1.07% on the evaluation set of the 2020 Fearless Steps Challenge, which sets a new state of the art."}],"publication":"INTERSPEECH 2020 Virtual Shanghai China","department":[{"_id":"54"}],"keyword":["voice activity detection","speech activity detection","neural network","statistical speech processing"],"type":"conference","date_created":"2020-11-25T15:03:19Z","file":[{"date_created":"2020-12-11T12:33:04Z","creator":"jensheit","success":1,"content_type":"application/pdf","file_id":"20697","access_level":"closed","file_size":998706,"file_name":"ms.pdf","date_updated":"2020-12-11T12:33:04Z","relation":"main_file"}],"date_updated":"2023-10-26T08:28:49Z","author":[{"full_name":"Heitkaemper, Jens","first_name":"Jens","last_name":"Heitkaemper","id":"27643"},{"id":"460","last_name":"Schmalenstroeer","first_name":"Joerg","full_name":"Schmalenstroeer, Joerg"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"title":"Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments","year":"2020","language":[{"iso":"eng"}]},{"status":"public","has_accepted_license":"1","page":"7004-7008","_id":"20762","ddc":["000"],"user_id":"49870","file_date_updated":"2020-12-16T14:09:48Z","citation":{"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.","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>.","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>","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>.","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>","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} }","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>."},"quality_controlled":"1","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"oa":"1","title":"End-to-End Training of Time Domain Audio Separation and Recognition","year":"2020","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","first_name":"Keisuke","last_name":"Kinoshita"},{"full_name":"Drude, Lukas","first_name":"Lukas","last_name":"Drude"},{"id":"40767","last_name":"Boeddeker","first_name":"Christoph","full_name":"Boeddeker, Christoph"},{"last_name":"Delcroix","first_name":"Marc","full_name":"Delcroix, Marc"},{"full_name":"Nakatani, Tomohiro","last_name":"Nakatani","first_name":"Tomohiro"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"date_updated":"2023-11-15T12:17:45Z","language":[{"iso":"eng"}],"doi":"10.1109/ICASSP40776.2020.9053461","publication":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","abstract":[{"lang":"eng","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."}],"file":[{"file_id":"20763","content_type":"application/pdf","file_name":"ICASSP_2020_vonNeumann_Paper.pdf","file_size":192529,"access_level":"open_access","relation":"main_file","date_updated":"2020-12-16T14:09:48Z","date_created":"2020-12-16T14:09:48Z","creator":"huesera"}],"date_created":"2020-12-16T14:07:54Z","type":"conference","department":[{"_id":"54"}]},{"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"quality_controlled":"1","citation":{"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>.","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.","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>.","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>","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} }","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>","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>."},"file_date_updated":"2020-12-16T14:14:14Z","oa":"1","has_accepted_license":"1","status":"public","user_id":"49870","ddc":["000"],"_id":"20764","page":"3097-3101","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. "}],"publication":"Proc. Interspeech 2020","department":[{"_id":"54"}],"type":"conference","date_created":"2020-12-16T14:12:45Z","file":[{"file_size":267893,"access_level":"open_access","file_name":"INTERSPEECH_2020_vonNeumann_Paper.pdf","date_updated":"2020-12-16T14:14:14Z","relation":"main_file","content_type":"application/pdf","file_id":"20765","creator":"huesera","date_created":"2020-12-16T14:14:14Z"}],"date_updated":"2023-11-15T12:17:57Z","author":[{"id":"49870","full_name":"von Neumann, Thilo","first_name":"Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670"},{"id":"40767","full_name":"Boeddeker, Christoph","last_name":"Boeddeker","first_name":"Christoph"},{"full_name":"Drude, Lukas","first_name":"Lukas","last_name":"Drude"},{"full_name":"Kinoshita, Keisuke","last_name":"Kinoshita","first_name":"Keisuke"},{"full_name":"Delcroix, Marc","first_name":"Marc","last_name":"Delcroix"},{"last_name":"Nakatani","first_name":"Tomohiro","full_name":"Nakatani, Tomohiro"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"title":"Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR","year":"2020","doi":"10.21437/Interspeech.2020-2519","language":[{"iso":"eng"}]},{"date_updated":"2023-11-17T06:23:39Z","has_accepted_license":"1","title":"Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network","status":"public","year":"2020","author":[{"last_name":"Gburrek","first_name":"Tobias","full_name":"Gburrek, Tobias","id":"44006"},{"id":"460","last_name":"Schmalenstroeer","first_name":"Joerg","full_name":"Schmalenstroeer, Joerg"},{"full_name":"Brendel, Andreas","first_name":"Andreas","last_name":"Brendel"},{"first_name":"Walter","last_name":"Kellermann","full_name":"Kellermann, Walter"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"user_id":"44006","ddc":["004"],"_id":"18651","language":[{"iso":"eng"}],"quality_controlled":"1","abstract":[{"text":"We present an approach to deep neural network based (DNN-based) distance estimation in reverberant rooms for supporting geometry calibration tasks in wireless acoustic sensor networks. Signal diffuseness information from acoustic signals is aggregated via the coherent-to-diffuse power ratio to obtain a distance-related feature, which is mapped to a source-to-microphone distance estimate by means of a DNN. This information is then combined with direction-of-arrival estimates from compact microphone arrays to infer the geometry of the sensor network. Unlike many other approaches to geometry calibration, the proposed scheme does only require that the sampling clocks of the sensor nodes are roughly synchronized. In simulations we show that the proposed DNN-based distance estimator generalizes to unseen acoustic environments and that precise estimates of the sensor node positions are obtained. ","lang":"eng"}],"file_date_updated":"2023-11-17T06:21:40Z","publication":"European Signal Processing Conference (EUSIPCO)","citation":{"ama":"Gburrek T, Schmalenstroeer J, Brendel A, Kellermann W, Haeb-Umbach R. Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network. In: <i>European Signal Processing Conference (EUSIPCO)</i>. ; 2020.","bibtex":"@inproceedings{Gburrek_Schmalenstroeer_Brendel_Kellermann_Haeb-Umbach_2020, title={Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network}, booktitle={European Signal Processing Conference (EUSIPCO)}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Brendel, Andreas and Kellermann, Walter and Haeb-Umbach, Reinhold}, year={2020} }","mla":"Gburrek, Tobias, et al. “Deep Neural Network Based Distance Estimation for Geometry Calibration in Acoustic Sensor Network.” <i>European Signal Processing Conference (EUSIPCO)</i>, 2020.","chicago":"Gburrek, Tobias, Joerg Schmalenstroeer, Andreas Brendel, Walter Kellermann, and Reinhold Haeb-Umbach. “Deep Neural Network Based Distance Estimation for Geometry Calibration in Acoustic Sensor Network.” In <i>European Signal Processing Conference (EUSIPCO)</i>, 2020.","short":"T. Gburrek, J. Schmalenstroeer, A. Brendel, W. Kellermann, R. Haeb-Umbach, in: European Signal Processing Conference (EUSIPCO), 2020.","apa":"Gburrek, T., Schmalenstroeer, J., Brendel, A., Kellermann, W., &#38; Haeb-Umbach, R. (2020). Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network. <i>European Signal Processing Conference (EUSIPCO)</i>.","ieee":"T. Gburrek, J. Schmalenstroeer, A. Brendel, W. Kellermann, and R. Haeb-Umbach, “Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Network,” 2020."},"type":"conference","department":[{"_id":"54"}],"oa":"1","file":[{"creator":"tgburrek","date_created":"2023-11-17T06:21:40Z","date_updated":"2023-11-17T06:21:40Z","relation":"main_file","file_size":292159,"access_level":"open_access","file_name":"Gburrek2020.pdf","content_type":"application/pdf","file_id":"48987"}],"date_created":"2020-08-31T07:20:57Z"},{"has_accepted_license":"1","status":"public","user_id":"49870","ddc":["000"],"_id":"20766","page":"2652-2656","quality_controlled":"1","citation":{"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} }","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>","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>.","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>.","short":"K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, R. Haeb-Umbach, in: Proc. Interspeech 2020, 2020, pp. 2652–2656.","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>.","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>"},"file_date_updated":"2020-12-16T14:16:32Z","oa":"1","date_updated":"2023-11-15T12:14:25Z","author":[{"full_name":"Kinoshita, Keisuke","first_name":"Keisuke","last_name":"Kinoshita"},{"full_name":"von Neumann, Thilo","last_name":"von Neumann","orcid":"https://orcid.org/0000-0002-7717-8670","first_name":"Thilo","id":"49870"},{"full_name":"Delcroix, Marc","first_name":"Marc","last_name":"Delcroix"},{"full_name":"Nakatani, Tomohiro","first_name":"Tomohiro","last_name":"Nakatani"},{"id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold"}],"year":"2020","title":"Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker Stream Separation","doi":"10.21437/Interspeech.2020-2388","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","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."}],"publication":"Proc. Interspeech 2020","department":[{"_id":"54"}],"type":"conference","date_created":"2020-12-16T14:15:24Z","file":[{"file_id":"20767","content_type":"application/pdf","relation":"main_file","date_updated":"2020-12-16T14:16:32Z","file_name":"INTERSPEECH_2020_vonNeumann1_Paper.pdf","access_level":"open_access","file_size":1725219,"date_created":"2020-12-16T14:16:32Z","creator":"huesera"}]},{"author":[{"id":"34851","last_name":"Ebbers","first_name":"Janek","full_name":"Ebbers, Janek"},{"id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold"}],"year":"2020","title":"Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection","date_updated":"2023-11-22T08:27:32Z","language":[{"iso":"eng"}],"publication":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)","abstract":[{"text":"In this paper we present our system for the detection and classification of acoustic scenes and events (DCASE) 2020 Challenge Task 4: Sound event detection and separation in domestic environments. We introduce two new models: the forward-backward convolutional recurrent neural network (FBCRNN) and the tag-conditioned convolutional neural network (CNN). The FBCRNN employs two recurrent neural network (RNN) classifiers sharing the same CNN for preprocessing. With one RNN processing a recording in forward direction and the other in backward direction, the two networks are trained to jointly predict audio tags, i.e., weak labels, at each time step within a recording, given that at each time step they have jointly processed the whole recording. The proposed training encourages the classifiers to tag events as soon as possible. Therefore, after training, the networks can be applied to shorter audio segments of, e.g., 200ms, allowing sound event detection (SED). Further, we propose a tag-conditioned CNN to complement SED. It is trained to predict strong labels while using (predicted) tags, i.e., weak labels, as additional input. For training pseudo strong labels from a FBCRNN ensemble are used. The presented system scored the fourth and third place in the systems and teams rankings, respectively. Subsequent improvements allow our system to even outperform the challenge baseline and winner systems in average by, respectively, 18.0% and 2.2% event-based F1-score on the validation set. Source code is publicly available at https://github.com/fgnt/pb_sed.","lang":"eng"}],"date_created":"2020-12-16T08:55:27Z","file":[{"creator":"huesera","date_created":"2020-12-16T08:57:22Z","relation":"main_file","date_updated":"2020-12-16T08:57:22Z","file_name":"DCASE2020Workshop_Ebbers_Paper.pdf","file_size":108326,"access_level":"open_access","file_id":"20754","content_type":"application/pdf"}],"department":[{"_id":"54"}],"type":"conference","status":"public","has_accepted_license":"1","_id":"20753","user_id":"34851","ddc":["000"],"citation":{"bibtex":"@inproceedings{Ebbers_Haeb-Umbach_2020, title={Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection}, booktitle={Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2020} }","ama":"Ebbers J, Haeb-Umbach R. Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection. In: <i>Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)</i>. ; 2020.","mla":"Ebbers, Janek, and Reinhold Haeb-Umbach. “Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection.” <i>Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)</i>, 2020.","chicago":"Ebbers, Janek, and Reinhold Haeb-Umbach. “Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection.” In <i>Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)</i>, 2020.","short":"J. Ebbers, R. Haeb-Umbach, in: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020), 2020.","ieee":"J. Ebbers and R. Haeb-Umbach, “Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection,” 2020.","apa":"Ebbers, J., &#38; Haeb-Umbach, R. (2020). Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-Supervised Sound Event Detection. <i>Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)</i>."},"file_date_updated":"2020-12-16T08:57:22Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"quality_controlled":"1","oa":"1"},{"_id":"20695","ddc":["000"],"user_id":"40767","status":"public","has_accepted_license":"1","oa":"1","file_date_updated":"2020-12-11T12:32:44Z","citation":{"apa":"Boeddeker, C., Nakatani, T., Kinoshita, K., &#38; Haeb-Umbach, R. (2020). Jointly Optimal Dereverberation and Beamforming. <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. <a href=\"https://doi.org/10.1109/icassp40776.2020.9054393\">https://doi.org/10.1109/icassp40776.2020.9054393</a>","ieee":"C. Boeddeker, T. Nakatani, K. Kinoshita, and R. Haeb-Umbach, “Jointly Optimal Dereverberation and Beamforming,” 2020, doi: <a href=\"https://doi.org/10.1109/icassp40776.2020.9054393\">10.1109/icassp40776.2020.9054393</a>.","chicago":"Boeddeker, Christoph, Tomohiro Nakatani, Keisuke Kinoshita, and Reinhold Haeb-Umbach. “Jointly Optimal Dereverberation and Beamforming.” In <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2020. <a href=\"https://doi.org/10.1109/icassp40776.2020.9054393\">https://doi.org/10.1109/icassp40776.2020.9054393</a>.","short":"C. Boeddeker, T. Nakatani, K. Kinoshita, R. Haeb-Umbach, in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.","mla":"Boeddeker, Christoph, et al. “Jointly Optimal Dereverberation and Beamforming.” <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2020, doi:<a href=\"https://doi.org/10.1109/icassp40776.2020.9054393\">10.1109/icassp40776.2020.9054393</a>.","ama":"Boeddeker C, Nakatani T, Kinoshita K, Haeb-Umbach R. Jointly Optimal Dereverberation and Beamforming. In: <i>ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2020. doi:<a href=\"https://doi.org/10.1109/icassp40776.2020.9054393\">10.1109/icassp40776.2020.9054393</a>","bibtex":"@inproceedings{Boeddeker_Nakatani_Kinoshita_Haeb-Umbach_2020, title={Jointly Optimal Dereverberation and Beamforming}, DOI={<a href=\"https://doi.org/10.1109/icassp40776.2020.9054393\">10.1109/icassp40776.2020.9054393</a>}, booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Boeddeker, Christoph and Nakatani, Tomohiro and Kinoshita, Keisuke and Haeb-Umbach, Reinhold}, year={2020} }"},"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"language":[{"iso":"eng"}],"doi":"10.1109/icassp40776.2020.9054393","year":"2020","title":"Jointly Optimal Dereverberation and Beamforming","author":[{"id":"40767","first_name":"Christoph","last_name":"Boeddeker","full_name":"Boeddeker, Christoph"},{"full_name":"Nakatani, Tomohiro","last_name":"Nakatani","first_name":"Tomohiro"},{"first_name":"Keisuke","last_name":"Kinoshita","full_name":"Kinoshita, Keisuke"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"publication_identifier":{"isbn":["9781509066315"]},"date_updated":"2024-11-14T09:17:32Z","publication_status":"published","file":[{"file_id":"20698","content_type":"application/pdf","file_name":"convBF.pdf","access_level":"open_access","file_size":200127,"relation":"main_file","date_updated":"2020-12-11T12:32:44Z","date_created":"2020-12-11T12:32:44Z","creator":"cbj"}],"date_created":"2020-12-11T12:28:49Z","type":"conference","department":[{"_id":"54"}],"publication":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"abstract":[{"lang":"eng","text":"Abstract Wenn akustische Signalverarbeitung mit automatisiertem Lernen verknüpft wird: Nachrichtentechniker arbeiten mit mehreren Mikrofonen und tiefen neuronalen Netzen an besserer Spracherkennung unter widrigsten Bedingungen. Von solchen Sensornetzwerken könnten langfristig auch digitale Sprachassistenten profitieren."}],"issue":"1","publication":"forschung","citation":{"mla":"Haeb-Umbach, Reinhold. “Lektionen Für Alexa \\&#38; Co?!” <i>Forschung</i>, vol. 44, no. 1, 2019, pp. 12–15, doi:<a href=\"https://doi.org/10.1002/fors.201970104\">10.1002/fors.201970104</a>.","bibtex":"@article{Haeb-Umbach_2019, title={Lektionen für Alexa \\&#38; Co?!}, volume={44}, DOI={<a href=\"https://doi.org/10.1002/fors.201970104\">10.1002/fors.201970104</a>}, number={1}, journal={forschung}, author={Haeb-Umbach, Reinhold}, year={2019}, pages={12–15} }","ama":"Haeb-Umbach R. Lektionen für Alexa \\&#38; Co?! <i>forschung</i>. 2019;44(1):12-15. doi:<a href=\"https://doi.org/10.1002/fors.201970104\">10.1002/fors.201970104</a>","ieee":"R. Haeb-Umbach, “Lektionen für Alexa \\&#38; Co?!,” <i>forschung</i>, vol. 44, no. 1, pp. 12–15, 2019.","apa":"Haeb-Umbach, R. (2019). Lektionen für Alexa \\&#38; Co?! <i>Forschung</i>, <i>44</i>(1), 12–15. <a href=\"https://doi.org/10.1002/fors.201970104\">https://doi.org/10.1002/fors.201970104</a>","chicago":"Haeb-Umbach, Reinhold. “Lektionen Für Alexa \\&#38; Co?!” <i>Forschung</i> 44, no. 1 (2019): 12–15. <a href=\"https://doi.org/10.1002/fors.201970104\">https://doi.org/10.1002/fors.201970104</a>.","short":"R. Haeb-Umbach, Forschung 44 (2019) 12–15."},"type":"journal_article","department":[{"_id":"54"}],"date_created":"2020-08-10T09:51:09Z","date_updated":"2022-01-06T06:53:19Z","intvolume":"        44","title":"Lektionen für Alexa \\& Co?!","status":"public","year":"2019","author":[{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"doi":"10.1002/fors.201970104","user_id":"44006","volume":44,"page":"12-15","_id":"17762","language":[{"iso":"eng"}]},{"date_created":"2020-09-16T07:59:46Z","file":[{"date_created":"2020-09-16T08:00:56Z","creator":"huesera","file_id":"19448","content_type":"application/pdf","file_name":"ArXiv_2019_Drude.pdf","access_level":"open_access","file_size":288594,"relation":"main_file","date_updated":"2020-12-11T12:22:31Z"}],"oa":"1","department":[{"_id":"54"}],"type":"journal_article","citation":{"short":"L. Drude, J. Heitkaemper, C. Boeddeker, R. Haeb-Umbach, ArXiv E-Prints (2019).","chicago":"Drude, Lukas, Jens Heitkaemper, Christoph Boeddeker, and Reinhold Haeb-Umbach. “SMS-WSJ: Database, Performance Measures, and Baseline Recipe for Multi-Channel Source Separation and Recognition.” <i>ArXiv E-Prints</i>, 2019.","ieee":"L. Drude, J. Heitkaemper, C. Boeddeker, and R. Haeb-Umbach, “SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition,” <i>ArXiv e-prints</i>, 2019.","apa":"Drude, L., Heitkaemper, J., Boeddeker, C., &#38; Haeb-Umbach, R. (2019). SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition. <i>ArXiv E-Prints</i>.","bibtex":"@article{Drude_Heitkaemper_Boeddeker_Haeb-Umbach_2019, title={SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition}, journal={ArXiv e-prints}, author={Drude, Lukas and Heitkaemper, Jens and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2019} }","ama":"Drude L, Heitkaemper J, Boeddeker C, Haeb-Umbach R. SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition. <i>ArXiv e-prints</i>. 2019.","mla":"Drude, Lukas, et al. “SMS-WSJ: Database, Performance Measures, and Baseline Recipe for Multi-Channel Source Separation and Recognition.” <i>ArXiv E-Prints</i>, 2019."},"publication":"ArXiv e-prints","file_date_updated":"2020-12-11T12:22:31Z","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"abstract":[{"text":"We present a multi-channel database of overlapping speech for training, evaluation, and detailed analysis of source separation and extraction algorithms: SMS-WSJ -- Spatialized Multi-Speaker Wall Street Journal. It consists of artificially mixed speech taken from the WSJ database, but unlike earlier databases we consider all WSJ0+1 utterances and take care of strictly separating the speaker sets present in the training, validation and test sets. When spatializing the data we ensure a high degree of randomness w.r.t. room size, array center and rotation, as well as speaker position. Furthermore, this paper offers a critical assessment of recently proposed measures of source separation performance. Alongside the code to generate the database we provide a source separation baseline and a Kaldi recipe with competitive word error rates to provide common ground for evaluation.","lang":"eng"}],"language":[{"iso":"eng"}],"_id":"19446","ddc":["000"],"user_id":"40767","author":[{"first_name":"Lukas","last_name":"Drude","full_name":"Drude, Lukas"},{"id":"27643","full_name":"Heitkaemper, Jens","first_name":"Jens","last_name":"Heitkaemper"},{"last_name":"Boeddeker","first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"year":"2019","status":"public","title":"SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition","has_accepted_license":"1","date_updated":"2022-01-06T06:54:04Z"},{"citation":{"bibtex":"@inproceedings{Drude_Heymann_Haeb-Umbach_2019, title={Unsupervised training of neural mask-based beamforming}, booktitle={INTERSPEECH 2019, Graz, Austria}, author={Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}, year={2019} }","ama":"Drude L, Heymann J, Haeb-Umbach R. Unsupervised training of neural mask-based beamforming. In: <i>INTERSPEECH 2019, Graz, Austria</i>. ; 2019.","mla":"Drude, Lukas, et al. “Unsupervised Training of Neural Mask-Based Beamforming.” <i>INTERSPEECH 2019, Graz, Austria</i>, 2019.","chicago":"Drude, Lukas, Jahn Heymann, and Reinhold Haeb-Umbach. “Unsupervised Training of Neural Mask-Based Beamforming.” In <i>INTERSPEECH 2019, Graz, Austria</i>, 2019.","short":"L. Drude, J. Heymann, R. Haeb-Umbach, in: INTERSPEECH 2019, Graz, Austria, 2019.","ieee":"L. Drude, J. Heymann, and R. Haeb-Umbach, “Unsupervised training of neural mask-based beamforming,” in <i>INTERSPEECH 2019, Graz, Austria</i>, 2019.","apa":"Drude, L., Heymann, J., &#38; Haeb-Umbach, R. (2019). Unsupervised training of neural mask-based beamforming. In <i>INTERSPEECH 2019, Graz, Austria</i>."},"file_date_updated":"2019-08-13T06:41:35Z","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"oa":"1","status":"public","has_accepted_license":"1","_id":"11965","ddc":["000"],"user_id":"59789","publication":"INTERSPEECH 2019, Graz, Austria","abstract":[{"lang":"eng","text":"We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the observations. It is trained from scratch without requiring any parallel data consisting of degraded input and clean training targets. Thus, training can be carried out on real recordings of noisy speech rather than simulated ones. In contrast to previous work on unsupervised training of neural mask estimators, our approach avoids the need for a possibly pre-trained teacher model entirely. We demonstrate the effectiveness of our approach by speech recognition experiments on two different datasets: one mainly deteriorated by noise (CHiME 4) and one by reverberation (REVERB). The results show that the performance of the proposed system is on par with a supervised system using oracle target masks for training and with a system trained using a model-based teacher."}],"date_created":"2019-07-18T09:11:39Z","file":[{"date_updated":"2019-08-13T06:41:35Z","relation":"main_file","access_level":"open_access","file_size":223413,"file_name":"INTERSPEECH_2019_Drude_Paper.pdf","content_type":"application/pdf","file_id":"12914","creator":"huesera","date_created":"2019-08-13T06:36:44Z"}],"department":[{"_id":"54"}],"type":"conference","author":[{"full_name":"Drude, Lukas","first_name":"Lukas","last_name":"Drude","id":"11213"},{"full_name":"Heymann, Jahn","first_name":"Jahn","last_name":"Heymann","id":"9168"},{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"}],"title":"Unsupervised training of neural mask-based beamforming","year":"2019","date_updated":"2022-01-06T06:51:14Z","language":[{"iso":"eng"}]},{"oa":"1","department":[{"_id":"54"}],"type":"conference","date_created":"2019-07-23T07:37:54Z","file":[{"file_id":"12925","content_type":"application/pdf","file_name":"ICASSP_2019_Drude_Paper.pdf","access_level":"open_access","file_size":368225,"relation":"main_file","date_updated":"2019-08-14T07:19:13Z","date_created":"2019-08-14T07:19:13Z","creator":"huesera"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"abstract":[{"text":"We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable. In particular, we demonstrate that an unsupervised spatial clustering algorithm is sufficient to guide the training of a deep clustering system. We argue that previous work on deep clustering requires strong supervision and elaborate on why this is a limitation. We demonstrate that (a) the single-channel deep clustering system trained according to the proposed scheme alone is able to achieve a similar performance as the multi-channel teacher in terms of word error rates and (b) initializing the spatial clustering approach with the deep clustering result yields a relative word error rate reduction of 26% over the unsupervised teacher.","lang":"eng"}],"citation":{"apa":"Drude, L., Hasenklever, D., &#38; Haeb-Umbach, R. (2019). Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation. In <i>ICASSP 2019, Brighton, UK</i>.","ieee":"L. Drude, D. Hasenklever, and R. Haeb-Umbach, “Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation,” in <i>ICASSP 2019, Brighton, UK</i>, 2019.","short":"L. Drude, D. Hasenklever, R. Haeb-Umbach, in: ICASSP 2019, Brighton, UK, 2019.","chicago":"Drude, Lukas, Daniel Hasenklever, and Reinhold Haeb-Umbach. “Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation.” In <i>ICASSP 2019, Brighton, UK</i>, 2019.","mla":"Drude, Lukas, et al. “Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation.” <i>ICASSP 2019, Brighton, UK</i>, 2019.","ama":"Drude L, Hasenklever D, Haeb-Umbach R. Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation. In: <i>ICASSP 2019, Brighton, UK</i>. ; 2019.","bibtex":"@inproceedings{Drude_Hasenklever_Haeb-Umbach_2019, title={Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation}, booktitle={ICASSP 2019, Brighton, UK}, author={Drude, Lukas and Hasenklever, Daniel and Haeb-Umbach, Reinhold}, year={2019} }"},"publication":"ICASSP 2019, Brighton, UK","file_date_updated":"2019-08-14T07:19:13Z","ddc":["000"],"user_id":"59789","_id":"12874","language":[{"iso":"eng"}],"has_accepted_license":"1","date_updated":"2022-01-06T06:51:21Z","author":[{"first_name":"Lukas","last_name":"Drude","full_name":"Drude, Lukas","id":"11213"},{"first_name":"Daniel","last_name":"Hasenklever","full_name":"Hasenklever, Daniel"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"year":"2019","title":"Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation","status":"public"},{"file_date_updated":"2019-12-17T07:28:06Z","publication":"ICASSP 2019, Brighton, UK","citation":{"apa":"Heymann, J., Drude, L., Haeb-Umbach, R., Kinoshita, K., &#38; Nakatani, T. (2019). Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR. In <i>ICASSP 2019, Brighton, UK</i>.","ieee":"J. Heymann, L. Drude, R. Haeb-Umbach, K. Kinoshita, and T. Nakatani, “Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR,” in <i>ICASSP 2019, Brighton, UK</i>, 2019.","chicago":"Heymann, Jahn, Lukas Drude, Reinhold Haeb-Umbach, Keisuke Kinoshita, and Tomohiro Nakatani. “Joint Optimization of Neural Network-Based WPE Dereverberation and Acoustic Model for Robust Online ASR.” In <i>ICASSP 2019, Brighton, UK</i>, 2019.","short":"J. Heymann, L. Drude, R. Haeb-Umbach, K. Kinoshita, T. Nakatani, in: ICASSP 2019, Brighton, UK, 2019.","mla":"Heymann, Jahn, et al. “Joint Optimization of Neural Network-Based WPE Dereverberation and Acoustic Model for Robust Online ASR.” <i>ICASSP 2019, Brighton, UK</i>, 2019.","ama":"Heymann J, Drude L, Haeb-Umbach R, Kinoshita K, Nakatani T. Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR. In: <i>ICASSP 2019, Brighton, UK</i>. ; 2019.","bibtex":"@inproceedings{Heymann_Drude_Haeb-Umbach_Kinoshita_Nakatani_2019, title={Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR}, booktitle={ICASSP 2019, Brighton, UK}, author={Heymann, Jahn and Drude, Lukas and Haeb-Umbach, Reinhold and Kinoshita, Keisuke and Nakatani, Tomohiro}, year={2019} }"},"abstract":[{"text":"Signal dereverberation using the Weighted Prediction Error (WPE) method has been proven to be an effective means to raise the accuracy of far-field speech recognition. First proposed as an iterative algorithm, follow-up works have reformulated it as a recursive least squares algorithm and therefore enabled its use in online applications. For this algorithm, the estimation of the power spectral density (PSD) of the anechoic signal plays an important role and strongly influences its performance. Recently, we showed that using a neural network PSD estimator leads to improved performance for online automatic speech recognition. This, however, comes at a price. To train the network, we require parallel data, i.e., utterances simultaneously available in clean and reverberated form. Here we propose to overcome this limitation by training the network jointly with the acoustic model of the speech recognizer. To be specific, the gradients computed from the cross-entropy loss between the target senone sequence and the acoustic model network output is backpropagated through the complex-valued dereverberation filter estimation to the neural network for PSD estimation. Evaluation on two databases demonstrates improved performance for on-line processing scenarios while imposing fewer requirements on the available training data and thus widening the range of applications.","lang":"eng"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"file":[{"date_updated":"2019-12-17T07:28:06Z","relation":"main_file","access_level":"open_access","file_size":199109,"file_name":"ICASSP_2019_Heymann_Paper.pdf","content_type":"application/pdf","file_id":"15334","creator":"huesera","date_created":"2019-12-17T07:28:06Z"}],"date_created":"2019-07-23T07:42:26Z","type":"conference","department":[{"_id":"54"}],"oa":"1","year":"2019","title":"Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR","status":"public","author":[{"id":"9168","first_name":"Jahn","last_name":"Heymann","full_name":"Heymann, Jahn"},{"id":"11213","full_name":"Drude, Lukas","last_name":"Drude","first_name":"Lukas"},{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"},{"last_name":"Kinoshita","first_name":"Keisuke","full_name":"Kinoshita, Keisuke"},{"first_name":"Tomohiro","last_name":"Nakatani","full_name":"Nakatani, Tomohiro"}],"date_updated":"2022-01-06T06:51:22Z","has_accepted_license":"1","language":[{"iso":"eng"}],"_id":"12875","user_id":"59789","ddc":["000"]}]