--- _id: '52958' author: - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Aswin Shanmugam full_name: Subramanian, Aswin Shanmugam last_name: Subramanian - first_name: Gordon full_name: Wichern, Gordon last_name: Wichern - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach - first_name: Jonathan full_name: Le Roux, Jonathan last_name: Le Roux citation: ama: 'Boeddeker C, Subramanian AS, Wichern G, Haeb-Umbach R, Le Roux J. TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2024;32:1185-1197. doi:10.1109/taslp.2024.3350887' apa: 'Boeddeker, C., Subramanian, A. S., Wichern, G., Haeb-Umbach, R., & Le Roux, J. (2024). TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 32, 1185–1197. https://doi.org/10.1109/taslp.2024.3350887' bibtex: '@article{Boeddeker_Subramanian_Wichern_Haeb-Umbach_Le Roux_2024, title={TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings}, volume={32}, DOI={10.1109/taslp.2024.3350887}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Boeddeker, Christoph and Subramanian, Aswin Shanmugam and Wichern, Gordon and Haeb-Umbach, Reinhold and Le Roux, Jonathan}, year={2024}, pages={1185–1197} }' chicago: 'Boeddeker, Christoph, Aswin Shanmugam Subramanian, Gordon Wichern, Reinhold Haeb-Umbach, and Jonathan Le Roux. “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.” IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024): 1185–97. https://doi.org/10.1109/taslp.2024.3350887.' ieee: 'C. Boeddeker, A. S. Subramanian, G. Wichern, R. Haeb-Umbach, and J. Le Roux, “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 1185–1197, 2024, doi: 10.1109/taslp.2024.3350887.' mla: 'Boeddeker, Christoph, et al. “TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, Institute of Electrical and Electronics Engineers (IEEE), 2024, pp. 1185–97, doi:10.1109/taslp.2024.3350887.' short: C. Boeddeker, A.S. Subramanian, G. Wichern, R. Haeb-Umbach, J. Le Roux, IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024) 1185–1197. date_created: 2024-03-26T16:11:54Z date_updated: 2024-03-26T16:16:34Z department: - _id: '54' doi: 10.1109/taslp.2024.3350887 intvolume: ' 32' keyword: - Electrical and Electronic Engineering - Acoustics and Ultrasonics - Computer Science (miscellaneous) - Computational Mathematics language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2303.03849 oa: '1' page: 1185-1197 publication: IEEE/ACM Transactions on Audio, Speech, and Language Processing publication_identifier: issn: - 2329-9290 - 2329-9304 publication_status: published publisher: Institute of Electrical and Electronics Engineers (IEEE) status: public title: 'TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings' type: journal_article user_id: '40767' volume: 32 year: '2024' ... --- _id: '48269' author: - first_name: Tobias full_name: Gburrek, Tobias id: '44006' last_name: Gburrek - first_name: Joerg full_name: Schmalenstroeer, Joerg id: '460' last_name: Schmalenstroeer - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Gburrek T, Schmalenstroeer J, Haeb-Umbach R. On the Integration of Sampling Rate Synchronization and Acoustic Beamforming. In: European Signal Processing Conference (EUSIPCO). ; 2023.' apa: Gburrek, T., Schmalenstroeer, J., & Haeb-Umbach, R. (2023). On the Integration of Sampling Rate Synchronization and Acoustic Beamforming. European Signal Processing Conference (EUSIPCO). European Signal Processing Conference (EUSIPCO), Helsinki. bibtex: '@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2023, title={On the Integration of Sampling Rate Synchronization and Acoustic Beamforming}, booktitle={European Signal Processing Conference (EUSIPCO)}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2023} }' chicago: Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “On the Integration of Sampling Rate Synchronization and Acoustic Beamforming.” In European Signal Processing Conference (EUSIPCO), 2023. ieee: T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “On the Integration of Sampling Rate Synchronization and Acoustic Beamforming,” presented at the European Signal Processing Conference (EUSIPCO), Helsinki, 2023. mla: Gburrek, Tobias, et al. “On the Integration of Sampling Rate Synchronization and Acoustic Beamforming.” European Signal Processing Conference (EUSIPCO), 2023. short: 'T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: European Signal Processing Conference (EUSIPCO), 2023.' conference: location: Helsinki name: European Signal Processing Conference (EUSIPCO) date_created: 2023-10-18T12:54:08Z date_updated: 2023-10-26T08:16:23Z department: - _id: '54' language: - iso: eng main_file_link: - open_access: '1' url: https://eurasip.org/Proceedings/Eusipco/Eusipco2023/pdfs/0000011.pdf oa: '1' publication: European Signal Processing Conference (EUSIPCO) quality_controlled: '1' status: public title: On the Integration of Sampling Rate Synchronization and Acoustic Beamforming type: conference user_id: '460' year: '2023' ... --- _id: '47128' author: - first_name: Tobias full_name: Cord-Landwehr, Tobias id: '44393' last_name: Cord-Landwehr - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Cătălin full_name: Zorilă, Cătălin last_name: Zorilă - first_name: Rama full_name: Doddipatla, Rama last_name: Doddipatla - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Cord-Landwehr T, Boeddeker C, Zorilă C, Doddipatla R, Haeb-Umbach R. Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. doi:10.1109/icassp49357.2023.10095370' apa: Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., & Haeb-Umbach, R. (2023). Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes. https://doi.org/10.1109/icassp49357.2023.10095370 bibtex: '@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization}, DOI={10.1109/icassp49357.2023.10095370}, 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} }' 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 ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023. https://doi.org/10.1109/icassp49357.2023.10095370. 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: 10.1109/icassp49357.2023.10095370.' mla: Cord-Landwehr, Tobias, et al. “Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.” ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, doi:10.1109/icassp49357.2023.10095370. 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.' conference: location: Rhodes name: 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) date_created: 2023-09-19T14:01:20Z date_updated: 2023-11-15T14:56:27Z ddc: - '000' department: - _id: '54' doi: 10.1109/icassp49357.2023.10095370 file: - access_level: open_access content_type: application/pdf creator: cord date_created: 2023-11-15T14:56:18Z date_updated: 2023-11-15T14:56:18Z file_id: '48932' file_name: teacher_student_embeddings.pdf file_size: 246306 relation: main_file file_date_updated: 2023-11-15T14:56:18Z has_accepted_license: '1' language: - iso: eng oa: '1' project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) publication_status: published publisher: IEEE status: public title: Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization type: conference user_id: '44393' year: '2023' ... --- _id: '48270' author: - first_name: Joerg full_name: Schmalenstroeer, Joerg id: '460' last_name: Schmalenstroeer - first_name: Tobias full_name: Gburrek, Tobias id: '44006' last_name: Gburrek - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Schmalenstroeer J, Gburrek T, Haeb-Umbach R. LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices. In: ITG Conference on Speech Communication. ; 2023.' apa: 'Schmalenstroeer, J., Gburrek, T., & Haeb-Umbach, R. (2023). LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices. ITG Conference on Speech Communication. ITG Conference on Speech Communication, Aachen.' bibtex: '@inproceedings{Schmalenstroeer_Gburrek_Haeb-Umbach_2023, title={LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices}, booktitle={ITG Conference on Speech Communication}, author={Schmalenstroeer, Joerg and Gburrek, Tobias and Haeb-Umbach, Reinhold}, year={2023} }' chicago: 'Schmalenstroeer, Joerg, Tobias Gburrek, and Reinhold Haeb-Umbach. “LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices.” In ITG Conference on Speech Communication, 2023.' ieee: 'J. Schmalenstroeer, T. Gburrek, and R. Haeb-Umbach, “LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices,” presented at the ITG Conference on Speech Communication, Aachen, 2023.' mla: 'Schmalenstroeer, Joerg, et al. “LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices.” ITG Conference on Speech Communication, 2023.' short: 'J. Schmalenstroeer, T. Gburrek, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2023.' conference: location: Aachen name: ITG Conference on Speech Communication date_created: 2023-10-18T13:00:54Z date_updated: 2023-11-15T14:48:45Z ddc: - '004' department: - _id: '54' file: - access_level: open_access content_type: application/pdf creator: schmalen date_created: 2023-10-26T08:20:15Z date_updated: 2023-11-15T14:48:44Z file_id: '48483' file_name: SchTgbHaeb2023Final.pdf file_size: 2844502 relation: main_file file_date_updated: 2023-11-15T14:48:44Z has_accepted_license: '1' language: - iso: eng oa: '1' publication: ITG Conference on Speech Communication quality_controlled: '1' status: public title: 'LibriWASN: A Data Set for Meeting Separation, Diarization, and Recognition with Asynchronous Recording Devices' type: conference user_id: '460' year: '2023' ... --- _id: '47129' author: - first_name: Tobias full_name: Cord-Landwehr, Tobias id: '44393' last_name: Cord-Landwehr - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Cătălin full_name: Zorilă, Cătălin last_name: Zorilă - first_name: Rama full_name: Doddipatla, Rama last_name: Doddipatla - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: 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: INTERSPEECH 2023. ISCA; 2023. doi:10.21437/interspeech.2023-1379' apa: Cord-Landwehr, T., Boeddeker, C., Zorilă, C., Doddipatla, R., & Haeb-Umbach, R. (2023). A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. INTERSPEECH 2023. https://doi.org/10.21437/interspeech.2023-1379 bibtex: '@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2023, title={A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures}, DOI={10.21437/interspeech.2023-1379}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}, year={2023} }' 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 INTERSPEECH 2023. ISCA, 2023. https://doi.org/10.21437/interspeech.2023-1379. 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: 10.21437/interspeech.2023-1379.' mla: Cord-Landwehr, Tobias, et al. “A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures.” INTERSPEECH 2023, ISCA, 2023, doi:10.21437/interspeech.2023-1379. short: 'T. Cord-Landwehr, C. Boeddeker, C. Zorilă, R. Doddipatla, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.' date_created: 2023-09-19T14:34:37Z date_updated: 2023-11-15T15:00:12Z ddc: - '000' department: - _id: '54' doi: 10.21437/interspeech.2023-1379 file: - access_level: open_access content_type: application/pdf creator: cord date_created: 2023-11-15T15:00:02Z date_updated: 2023-11-15T15:00:02Z file_id: '48933' file_name: multispeaker_embeddings.pdf file_size: 303203 relation: main_file file_date_updated: 2023-11-15T15:00:02Z has_accepted_license: '1' language: - iso: eng oa: '1' project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: INTERSPEECH 2023 publication_status: published publisher: ISCA status: public title: A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures type: conference user_id: '44393' year: '2023' ... --- _id: '48355' abstract: - lang: eng text: "Unsupervised speech disentanglement aims at separating fast varying from\r\nslowly varying components of a speech signal. In this contribution, we take a\r\ncloser look at the embedding vector representing the slowly varying signal\r\ncomponents, commonly named the speaker embedding vector. We ask, which\r\nproperties of a speaker's voice are captured and investigate to which extent do\r\nindividual embedding vector components sign responsible for them, using the\r\nconcept of Shapley values. Our findings show that certain speaker-specific\r\nacoustic-phonetic properties can be fairly well predicted from the speaker\r\nembedding, while the investigated more abstract voice quality features cannot." author: - first_name: Frederik full_name: Rautenberg, Frederik id: '72602' last_name: Rautenberg - first_name: Michael full_name: Kuhlmann, Michael id: '49871' last_name: Kuhlmann - first_name: Jana full_name: Wiechmann, Jana last_name: Wiechmann - first_name: Fritz full_name: Seebauer, Fritz last_name: Seebauer - first_name: Petra full_name: Wagner, Petra last_name: Wagner - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Rautenberg F, Kuhlmann M, Wiechmann J, Seebauer F, Wagner P, Haeb-Umbach R. On Feature Importance and Interpretability of Speaker Representations. In: ITG Conference on Speech Communication. ; 2023.' apa: Rautenberg, F., Kuhlmann, M., Wiechmann, J., Seebauer, F., Wagner, P., & Haeb-Umbach, R. (2023). On Feature Importance and Interpretability of Speaker Representations. ITG Conference on Speech Communication. ITG Conference on Speech Communication, Aachen. bibtex: '@inproceedings{Rautenberg_Kuhlmann_Wiechmann_Seebauer_Wagner_Haeb-Umbach_2023, title={On Feature Importance and Interpretability of Speaker Representations}, booktitle={ITG Conference on Speech Communication}, author={Rautenberg, Frederik and Kuhlmann, Michael and Wiechmann, Jana and Seebauer, Fritz and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2023} }' chicago: Rautenberg, Frederik, Michael Kuhlmann, Jana Wiechmann, Fritz Seebauer, Petra Wagner, and Reinhold Haeb-Umbach. “On Feature Importance and Interpretability of Speaker Representations.” In ITG Conference on Speech Communication, 2023. ieee: F. Rautenberg, M. Kuhlmann, J. Wiechmann, F. Seebauer, P. Wagner, and R. Haeb-Umbach, “On Feature Importance and Interpretability of Speaker Representations,” presented at the ITG Conference on Speech Communication, Aachen, 2023. mla: Rautenberg, Frederik, et al. “On Feature Importance and Interpretability of Speaker Representations.” ITG Conference on Speech Communication, 2023. short: 'F. Rautenberg, M. Kuhlmann, J. Wiechmann, F. Seebauer, P. Wagner, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2023.' conference: end_date: 2023-09-22 location: Aachen name: ITG Conference on Speech Communication start_date: 2023-09-20 date_created: 2023-10-20T08:04:46Z date_updated: 2023-11-22T13:44:33Z ddc: - '000' department: - _id: '54' - _id: '660' external_id: arxiv: - '2310.12599' file: - access_level: closed content_type: application/pdf creator: frra date_created: 2023-10-20T08:20:58Z date_updated: 2023-10-20T08:20:58Z file_id: '48359' file_name: arxiv.pdf file_size: 272390 relation: main_file success: 1 file_date_updated: 2023-10-20T08:20:58Z has_accepted_license: '1' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2310.12599 oa: '1' project: - _id: '129' grant_number: '438445824' name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)' publication: ITG Conference on Speech Communication status: public title: On Feature Importance and Interpretability of Speaker Representations type: conference user_id: '72602' year: '2023' ... --- _id: '48410' author: - first_name: Jana full_name: Wiechmann, Jana last_name: Wiechmann - first_name: Frederik full_name: Rautenberg, Frederik id: '72602' last_name: Rautenberg - first_name: Petra full_name: Wagner, Petra last_name: Wagner - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Wiechmann J, Rautenberg F, Wagner P, Haeb-Umbach R. Explaining voice characteristics to novice voice practitioners-How successful is it? In: 20th International Congress of the Phonetic Sciences (ICPhS) . ; 2023.' apa: Wiechmann, J., Rautenberg, F., Wagner, P., & Haeb-Umbach, R. (2023). Explaining voice characteristics to novice voice practitioners-How successful is it? 20th International Congress of the Phonetic Sciences (ICPhS) . bibtex: '@inproceedings{Wiechmann_Rautenberg_Wagner_Haeb-Umbach_2023, title={Explaining voice characteristics to novice voice practitioners-How successful is it?}, booktitle={20th International Congress of the Phonetic Sciences (ICPhS) }, author={Wiechmann, Jana and Rautenberg, Frederik and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2023} }' chicago: Wiechmann, Jana, Frederik Rautenberg, Petra Wagner, and Reinhold Haeb-Umbach. “Explaining Voice Characteristics to Novice Voice Practitioners-How Successful Is It?” In 20th International Congress of the Phonetic Sciences (ICPhS) , 2023. ieee: J. Wiechmann, F. Rautenberg, P. Wagner, and R. Haeb-Umbach, “Explaining voice characteristics to novice voice practitioners-How successful is it?,” 2023. mla: Wiechmann, Jana, et al. “Explaining Voice Characteristics to Novice Voice Practitioners-How Successful Is It?” 20th International Congress of the Phonetic Sciences (ICPhS) , 2023. short: 'J. Wiechmann, F. Rautenberg, P. Wagner, R. Haeb-Umbach, in: 20th International Congress of the Phonetic Sciences (ICPhS) , 2023.' conference: end_date: 2023-08-11 start_date: 2023-08-07 date_created: 2023-10-24T08:05:40Z date_updated: 2023-11-22T13:44:59Z ddc: - '040' department: - _id: '54' - _id: '660' file: - access_level: closed content_type: application/pdf creator: frra date_created: 2023-10-24T08:03:27Z date_updated: 2023-10-24T08:03:27Z file_id: '48413' file_name: 188.pdf file_size: 209980 relation: main_file success: 1 file_date_updated: 2023-10-24T08:03:27Z has_accepted_license: '1' language: - iso: eng main_file_link: - open_access: '1' oa: '1' project: - _id: '129' grant_number: '438445824' name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)' publication: '20th International Congress of the Phonetic Sciences (ICPhS) ' status: public title: Explaining voice characteristics to novice voice practitioners-How successful is it? type: conference user_id: '72602' year: '2023' ... --- _id: '48390' author: - first_name: Simon full_name: Berger, Simon last_name: Berger - first_name: Peter full_name: Vieting, Peter last_name: Vieting - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Ralf full_name: Schlüter, Ralf last_name: Schlüter - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Berger S, Vieting P, Boeddeker C, Schlüter R, Haeb-Umbach R. Mixture Encoder for Joint Speech Separation and Recognition. In: INTERSPEECH 2023. ISCA; 2023. doi:10.21437/interspeech.2023-1815' apa: Berger, S., Vieting, P., Boeddeker, C., Schlüter, R., & Haeb-Umbach, R. (2023). Mixture Encoder for Joint Speech Separation and Recognition. INTERSPEECH 2023. https://doi.org/10.21437/interspeech.2023-1815 bibtex: '@inproceedings{Berger_Vieting_Boeddeker_Schlüter_Haeb-Umbach_2023, title={Mixture Encoder for Joint Speech Separation and Recognition}, DOI={10.21437/interspeech.2023-1815}, booktitle={INTERSPEECH 2023}, publisher={ISCA}, author={Berger, Simon and Vieting, Peter and Boeddeker, Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2023} }' chicago: Berger, Simon, Peter Vieting, Christoph Boeddeker, Ralf Schlüter, and Reinhold Haeb-Umbach. “Mixture Encoder for Joint Speech Separation and Recognition.” In INTERSPEECH 2023. ISCA, 2023. https://doi.org/10.21437/interspeech.2023-1815. ieee: 'S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach, “Mixture Encoder for Joint Speech Separation and Recognition,” 2023, doi: 10.21437/interspeech.2023-1815.' mla: Berger, Simon, et al. “Mixture Encoder for Joint Speech Separation and Recognition.” INTERSPEECH 2023, ISCA, 2023, doi:10.21437/interspeech.2023-1815. short: 'S. Berger, P. Vieting, C. Boeddeker, R. Schlüter, R. Haeb-Umbach, in: INTERSPEECH 2023, ISCA, 2023.' date_created: 2023-10-23T15:06:39Z date_updated: 2023-10-23T15:10:19Z department: - _id: '54' doi: 10.21437/interspeech.2023-1815 language: - iso: eng publication: INTERSPEECH 2023 publication_status: published publisher: ISCA status: public title: Mixture Encoder for Joint Speech Separation and Recognition type: conference user_id: '40767' year: '2023' ... --- _id: '46069' author: - first_name: Fritz full_name: Seebauer, Fritz last_name: Seebauer - first_name: Michael full_name: Kuhlmann, Michael id: '49871' last_name: Kuhlmann - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach - first_name: Petra full_name: Wagner, Petra last_name: Wagner citation: ama: 'Seebauer F, Kuhlmann M, Haeb-Umbach R, Wagner P. Re-examining the quality dimensions of synthetic speech. In: 12th Speech Synthesis Workshop (SSW) 2023. ; 2023.' apa: Seebauer, F., Kuhlmann, M., Haeb-Umbach, R., & Wagner, P. (2023). Re-examining the quality dimensions of synthetic speech. 12th Speech Synthesis Workshop (SSW) 2023. bibtex: '@inproceedings{Seebauer_Kuhlmann_Haeb-Umbach_Wagner_2023, title={Re-examining the quality dimensions of synthetic speech}, booktitle={12th Speech Synthesis Workshop (SSW) 2023}, author={Seebauer, Fritz and Kuhlmann, Michael and Haeb-Umbach, Reinhold and Wagner, Petra}, year={2023} }' chicago: Seebauer, Fritz, Michael Kuhlmann, Reinhold Haeb-Umbach, and Petra Wagner. “Re-Examining the Quality Dimensions of Synthetic Speech.” In 12th Speech Synthesis Workshop (SSW) 2023, 2023. ieee: F. Seebauer, M. Kuhlmann, R. Haeb-Umbach, and P. Wagner, “Re-examining the quality dimensions of synthetic speech,” 2023. mla: Seebauer, Fritz, et al. “Re-Examining the Quality Dimensions of Synthetic Speech.” 12th Speech Synthesis Workshop (SSW) 2023, 2023. short: 'F. Seebauer, M. Kuhlmann, R. Haeb-Umbach, P. Wagner, in: 12th Speech Synthesis Workshop (SSW) 2023, 2023.' date_created: 2023-07-15T16:10:20Z date_updated: 2023-10-25T08:42:56Z department: - _id: '54' has_accepted_license: '1' language: - iso: eng project: - _id: '129' grant_number: '438445824' name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)' publication: 12th Speech Synthesis Workshop (SSW) 2023 status: public title: Re-examining the quality dimensions of synthetic speech type: conference user_id: '242' year: '2023' ... --- _id: '35602' abstract: - lang: eng text: "Continuous Speech Separation (CSS) has been proposed to address speech overlaps during the analysis of realistic meeting-like conversations by eliminating any overlaps before further processing.\r\nCSS separates a recording of arbitrarily many speakers into a small number of overlap-free output channels, where each output channel may contain speech of multiple speakers.\r\nThis is often done by applying a conventional separation model trained with Utterance-level Permutation Invariant Training (uPIT), which exclusively maps a speaker to an output channel, in sliding window approach called stitching.\r\nRecently, we introduced an alternative training scheme called Graph-PIT that teaches the separation network to directly produce output streams in the required format without stitching.\r\nIt can handle an arbitrary number of speakers as long as never more of them overlap at the same time than the separator has output channels.\r\nIn this contribution, we further investigate the Graph-PIT training scheme.\r\nWe show in extended experiments that models trained with Graph-PIT also work in challenging reverberant conditions.\r\nModels trained in this way are able to perform segment-less CSS, i.e., without stitching, and achieve comparable and often better separation quality than the conventional CSS with uPIT and stitching.\r\nWe simplify the training schedule for Graph-PIT with the recently proposed Source Aggregated Signal-to-Distortion Ratio (SA-SDR) loss.\r\nIt eliminates unfavorable properties of the previously used A-SDR loss and thus enables training with Graph-PIT from scratch.\r\nGraph-PIT training relaxes the constraints w.r.t. the allowed numbers of speakers and speaking patterns which allows using a larger variety of training data.\r\nFurthermore, we introduce novel signal-level evaluation metrics for meeting scenarios, namely the source-aggregated scale- and convolution-invariant Signal-to-Distortion Ratio (SA-SI-SDR and SA-CI-SDR), which are generalizations of the commonly used SDR-based metrics for the CSS case." article_type: original author: - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Keisuke full_name: Kinoshita, Keisuke last_name: Kinoshita - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Marc full_name: Delcroix, Marc last_name: Delcroix - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2023;31:576-589. doi:10.1109/taslp.2022.3228629' apa: 'von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2023). Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 576–589. https://doi.org/10.1109/taslp.2022.3228629' bibtex: '@article{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2023, title={Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria}, volume={31}, DOI={10.1109/taslp.2022.3228629}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2023}, pages={576–589} }' chicago: 'Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach. “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria.” IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023): 576–89. https://doi.org/10.1109/taslp.2022.3228629.' ieee: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 576–589, 2023, doi: 10.1109/taslp.2022.3228629.' mla: 'von Neumann, Thilo, et al. “Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria.” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, Institute of Electrical and Electronics Engineers (IEEE), 2023, pp. 576–89, doi:10.1109/taslp.2022.3228629.' short: T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023) 576–589. date_created: 2023-01-09T17:24:17Z date_updated: 2023-11-15T12:16:11Z ddc: - '000' department: - _id: '54' doi: 10.1109/taslp.2022.3228629 file: - access_level: open_access content_type: application/pdf creator: haebumb date_created: 2023-01-09T17:46:05Z date_updated: 2023-01-11T08:50:19Z file_id: '35607' file_name: main.pdf file_size: 7185077 relation: main_file file_date_updated: 2023-01-11T08:50:19Z has_accepted_license: '1' intvolume: ' 31' keyword: - Continuous Speech Separation - Source Separation - Graph-PIT - Dynamic Programming - Permutation Invariant Training language: - iso: eng oa: '1' page: 576-589 project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: IEEE/ACM Transactions on Audio, Speech, and Language Processing publication_identifier: issn: - 2329-9290 - 2329-9304 publication_status: published publisher: Institute of Electrical and Electronics Engineers (IEEE) quality_controlled: '1' status: public title: 'Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria' type: journal_article user_id: '49870' volume: 31 year: '2023' ... --- _id: '48281' 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." author: - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Keisuke full_name: Kinoshita, Keisuke last_name: Kinoshita - first_name: Marc full_name: Delcroix, Marc last_name: Delcroix - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach 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: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. doi:10.1109/icassp49357.2023.10094784' apa: von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., & Haeb-Umbach, R. (2023). On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10094784 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={10.1109/icassp49357.2023.10094784}, 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} }' 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 ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023. https://doi.org/10.1109/icassp49357.2023.10094784. 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: 10.1109/icassp49357.2023.10094784.' mla: von Neumann, Thilo, et al. “On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems.” ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2023, doi:10.1109/icassp49357.2023.10094784. 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.' date_created: 2023-10-19T07:38:31Z date_updated: 2023-11-15T12:14:15Z ddc: - '000' department: - _id: '54' doi: 10.1109/icassp49357.2023.10094784 file: - access_level: open_access content_type: application/pdf creator: tvn date_created: 2023-10-19T07:39:57Z date_updated: 2023-10-19T07:41:56Z file_id: '48282' file_name: ICASSP_2023_Meeting_Evaluation.pdf file_size: 204994 relation: main_file file_date_updated: 2023-10-19T07:41:56Z has_accepted_license: '1' keyword: - Word Error Rate - Meeting Recognition - Levenshtein Distance language: - iso: eng main_file_link: - url: https://ieeexplore.ieee.org/document/10094784 oa: '1' publication: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) publication_status: published publisher: IEEE quality_controlled: '1' related_material: link: - relation: software url: https://github.com/fgnt/meeteval status: public title: On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems type: conference user_id: '49870' year: '2023' ... --- _id: '48275' 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." author: - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Marc full_name: Delcroix, Marc last_name: Delcroix - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'von Neumann T, Boeddeker C, Delcroix M, Haeb-Umbach R. MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. In: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments. ; 2023.' apa: 'von Neumann, T., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2023). MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems. Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments. CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin.' bibtex: '@inproceedings{von Neumann_Boeddeker_Delcroix_Haeb-Umbach_2023, title={MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems}, booktitle={Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments}, author={von Neumann, Thilo and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2023} }' 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 Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.' ieee: 'T. von Neumann, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems,” presented at the CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin, 2023.' mla: 'von Neumann, Thilo, et al. “MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems.” Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.' short: 'T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments, 2023.' conference: location: Dublin name: CHiME 2023 Workshop on Speech Processing in Everyday Environments date_created: 2023-10-19T07:24:51Z date_updated: 2023-11-15T12:14:02Z ddc: - '000' department: - _id: '54' file: - access_level: open_access content_type: application/pdf creator: tvn date_created: 2023-10-19T07:19:59Z date_updated: 2023-10-19T07:19:59Z file_id: '48276' file_name: Chime_7__MeetEval.pdf file_size: 263744 relation: main_file file_date_updated: 2023-10-19T07:19:59Z has_accepted_license: '1' keyword: - Speech Recognition - Word Error Rate - Meeting Transcription language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2307.11394 oa: '1' project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments quality_controlled: '1' related_material: link: - relation: software url: https://github.com/fgnt/meeteval status: public title: 'MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems' type: conference user_id: '49870' year: '2023' ... --- _id: '49109' abstract: - lang: eng text: "We propose a diarization system, that estimates “who spoke when” based on spatial information, to be used as a front-end of a meeting transcription system running on the signals gathered from an acoustic sensor network (ASN). Although the\r\nspatial distribution of the microphones is advantageous, exploiting the spatial diversity for diarization and signal enhancement is challenging, because the microphones’ positions are typically unknown, and the recorded signals are initially unsynchronized in general. Here, we approach these issues by first blindly synchronizing the signals and then estimating time differences of arrival (TDOAs). The TDOA information is exploited to estimate the speakers’ activity, even in the presence of multiple speakers being simultaneously active. This speaker activity information serves as a guide for a spatial mixture model, on which basis the individual speaker’s signals are extracted via beamforming. Finally, the extracted signals are forwarded to a speech recognizer. Additionally, a novel initialization scheme for spatial mixture models based on the TDOA estimates is proposed. Experiments conducted on real recordings from the LibriWASN data set have shown that our proposed system is advantageous compared to a system using a spatial mixture model, which does not make use\r\nof external diarization information." author: - first_name: Tobias full_name: Gburrek, Tobias id: '44006' last_name: Gburrek - first_name: Joerg full_name: Schmalenstroeer, Joerg id: '460' last_name: Schmalenstroeer - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Gburrek T, Schmalenstroeer J, Haeb-Umbach R. Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks. In: Proc. Asilomar Conference on Signals, Systems, and Computers. ; 2023.' apa: Gburrek, T., Schmalenstroeer, J., & Haeb-Umbach, R. (2023). Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks. Proc. Asilomar Conference on Signals, Systems, and Computers. 57th Asilomar Conference on Signals, Systems, and Computers. bibtex: '@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2023, title={Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks}, booktitle={Proc. Asilomar Conference on Signals, Systems, and Computers}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2023} }' chicago: Gburrek, Tobias, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks.” In Proc. Asilomar Conference on Signals, Systems, and Computers, 2023. ieee: T. Gburrek, J. Schmalenstroeer, and R. Haeb-Umbach, “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks,” presented at the 57th Asilomar Conference on Signals, Systems, and Computers, 2023. mla: Gburrek, Tobias, et al. “Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks.” Proc. Asilomar Conference on Signals, Systems, and Computers, 2023. short: 'T. Gburrek, J. Schmalenstroeer, R. Haeb-Umbach, in: Proc. Asilomar Conference on Signals, Systems, and Computers, 2023.' conference: end_date: 2023-11-01 name: 57th Asilomar Conference on Signals, Systems, and Computers start_date: 2023-10-31 date_created: 2023-11-22T07:52:29Z date_updated: 2023-11-22T07:58:49Z ddc: - '004' department: - _id: '54' file: - access_level: open_access content_type: application/pdf creator: schmalen date_created: 2023-11-22T07:51:18Z date_updated: 2023-11-22T07:58:49Z file_id: '49110' file_name: asilomar.pdf file_size: 212317 relation: main_file file_date_updated: 2023-11-22T07:58:49Z has_accepted_license: '1' keyword: - Diarization - time difference of arrival - ad-hoc acoustic sensor network - meeting transcription language: - iso: eng oa: '1' publication: Proc. Asilomar Conference on Signals, Systems, and Computers quality_controlled: '1' status: public title: Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks type: conference user_id: '460' year: '2023' ... --- _id: '44849' author: - first_name: Frederik full_name: Rautenberg, Frederik id: '72602' last_name: Rautenberg - first_name: Michael full_name: Kuhlmann, Michael id: '49871' last_name: Kuhlmann - first_name: Janek full_name: Ebbers, Janek id: '34851' last_name: Ebbers - first_name: Jana full_name: Wiechmann, Jana last_name: Wiechmann - first_name: Fritz full_name: Seebauer, Fritz last_name: Seebauer - first_name: Petra full_name: Wagner, Petra last_name: Wagner - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Rautenberg F, Kuhlmann M, Ebbers J, et al. Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics. In: Fortschritte Der Akustik - DAGA 2023. ; 2023:1409-1412.' apa: Rautenberg, F., Kuhlmann, M., Ebbers, J., Wiechmann, J., Seebauer, F., Wagner, P., & Haeb-Umbach, R. (2023). Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics. Fortschritte Der Akustik - DAGA 2023, 1409–1412. bibtex: '@inproceedings{Rautenberg_Kuhlmann_Ebbers_Wiechmann_Seebauer_Wagner_Haeb-Umbach_2023, title={Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics}, booktitle={Fortschritte der Akustik - DAGA 2023}, author={Rautenberg, Frederik and Kuhlmann, Michael and Ebbers, Janek and Wiechmann, Jana and Seebauer, Fritz and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2023}, pages={1409–1412} }' chicago: Rautenberg, Frederik, Michael Kuhlmann, Janek Ebbers, Jana Wiechmann, Fritz Seebauer, Petra Wagner, and Reinhold Haeb-Umbach. “Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics.” In Fortschritte Der Akustik - DAGA 2023, 1409–12, 2023. ieee: F. Rautenberg et al., “Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics,” in Fortschritte der Akustik - DAGA 2023, Hamburg, 2023, pp. 1409–1412. mla: Rautenberg, Frederik, et al. “Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics.” Fortschritte Der Akustik - DAGA 2023, 2023, pp. 1409–12. short: 'F. Rautenberg, M. Kuhlmann, J. Ebbers, J. Wiechmann, F. Seebauer, P. Wagner, R. Haeb-Umbach, in: Fortschritte Der Akustik - DAGA 2023, 2023, pp. 1409–1412.' conference: end_date: 2023-03-09 location: Hamburg name: DAGA 2023 - 49. Jahrestagung für Akustik start_date: 2023-03-06 date_created: 2023-05-15T08:48:54Z date_updated: 2024-02-29T17:05:16Z ddc: - '000' department: - _id: '54' - _id: '660' file: - access_level: open_access content_type: application/pdf creator: frra date_created: 2024-02-29T16:15:12Z date_updated: 2024-02-29T16:15:12Z file_id: '52221' file_name: Daga_2023_Rautenberg_Paper.pdf file_size: 289493 relation: main_file file_date_updated: 2024-02-29T16:15:12Z has_accepted_license: '1' language: - iso: eng main_file_link: - open_access: '1' url: https://pub.dega-akustik.de/DAGA_2023/data/articles/000105.pdf oa: '1' page: 1409-1412 project: - _id: '129' grant_number: '438445824' name: 'TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)' publication: Fortschritte der Akustik - DAGA 2023 publication_status: published status: public title: Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics type: conference user_id: '72602' year: '2023' ... --- _id: '33954' author: - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Tobias full_name: Cord-Landwehr, Tobias id: '44393' last_name: Cord-Landwehr - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. An Initialization Scheme for Meeting Separation with Spatial Mixture Models. In: Interspeech 2022. ISCA; 2022. doi:10.21437/interspeech.2022-10929' apa: Boeddeker, C., Cord-Landwehr, T., von Neumann, T., & Haeb-Umbach, R. (2022). An Initialization Scheme for Meeting Separation with Spatial Mixture Models. Interspeech 2022. https://doi.org/10.21437/interspeech.2022-10929 bibtex: '@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2022, title={An Initialization Scheme for Meeting Separation with Spatial Mixture Models}, DOI={10.21437/interspeech.2022-10929}, booktitle={Interspeech 2022}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2022} }' chicago: Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold Haeb-Umbach. “An Initialization Scheme for Meeting Separation with Spatial Mixture Models.” In Interspeech 2022. ISCA, 2022. https://doi.org/10.21437/interspeech.2022-10929. ieee: 'C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “An Initialization Scheme for Meeting Separation with Spatial Mixture Models,” 2022, doi: 10.21437/interspeech.2022-10929.' mla: Boeddeker, Christoph, et al. “An Initialization Scheme for Meeting Separation with Spatial Mixture Models.” Interspeech 2022, ISCA, 2022, doi:10.21437/interspeech.2022-10929. short: 'C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: Interspeech 2022, ISCA, 2022.' date_created: 2022-10-28T10:53:56Z date_updated: 2022-10-28T10:57:22Z department: - _id: '54' doi: 10.21437/interspeech.2022-10929 language: - iso: eng main_file_link: - open_access: '1' url: https://www.isca-speech.org/archive/pdfs/interspeech_2022/boeddeker22_interspeech.pdf oa: '1' project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: Interspeech 2022 publication_status: published publisher: ISCA status: public title: An Initialization Scheme for Meeting Separation with Spatial Mixture Models type: conference user_id: '40767' year: '2022' ... --- _id: '33471' 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." author: - first_name: Jens full_name: Heitkämper, Jens id: '27643' last_name: Heitkämper - first_name: Joerg full_name: Schmalenstroeer, Joerg id: '460' last_name: Schmalenstroeer - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Heitkämper J, Schmalenstroeer J, Haeb-Umbach R. Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels. In: Proceedings of the 30th European Signal Processing Conference (EUSIPCO).' apa: Heitkämper, J., Schmalenstroeer, J., & Haeb-Umbach, R. (n.d.). Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels. Proceedings of the 30th European Signal Processing Conference (EUSIPCO). 30th European Signal Processing Conference (EUSIPCO), Belgrad. 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} }' chicago: Heitkämper, Jens, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels.” In Proceedings of the 30th European Signal Processing Conference (EUSIPCO). 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. mla: Heitkämper, Jens, et al. “Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels.” Proceedings of the 30th European Signal Processing Conference (EUSIPCO). short: 'J. Heitkämper, J. Schmalenstroeer, R. Haeb-Umbach, in: Proceedings of the 30th European Signal Processing Conference (EUSIPCO), Belgrad, n.d.' conference: end_date: 2022-09-02 location: Belgrad name: 30th European Signal Processing Conference (EUSIPCO) start_date: 2022-08-29 date_created: 2022-09-22T10:56:13Z date_updated: 2023-10-26T08:15:57Z ddc: - '000' department: - _id: '54' file: - access_level: closed content_type: application/pdf creator: jensheit date_created: 2022-09-22T10:48:31Z date_updated: 2022-09-22T10:48:31Z file_id: '33472' file_name: cfo.pdf file_size: 1231379 relation: main_file success: 1 file_date_updated: 2022-09-22T10:48:31Z has_accepted_license: '1' language: - iso: eng place: Belgrad project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: Proceedings of the 30th European Signal Processing Conference (EUSIPCO) publication_status: accepted quality_controlled: '1' status: public title: Neural Network Based Carrier Frequency Offset Estimation From Speech Transmitted Over High Frequency Channels type: conference user_id: '460' year: '2022' ... --- _id: '33958' abstract: - lang: eng text: Recent speaker diarization studies showed that integration of end-to-end neural diarization (EEND) and clustering-based diarization is a promising approach for achieving state-of-the-art performance on various tasks. Such an approach first divides an observed signal into fixed-length segments, then performs {\it segment-level} local diarization based on an EEND module, and merges the segment-level results via clustering to form a final global diarization result. The segmentation is done to limit the number of speakers in each segment since the current EEND cannot handle a large number of speakers. In this paper, we argue that such an approach involving the segmentation has several issues; for example, it inevitably faces a dilemma that larger segment sizes increase both the context available for enhancing the performance and the number of speakers for the local EEND module to handle. To resolve such a problem, this paper proposes a novel framework that performs diarization without segmentation. However, it can still handle challenging data containing many speakers and a significant amount of overlapping speech. The proposed method can take an entire meeting for inference and perform {\it utterance-by-utterance} diarization that clusters utterance activities in terms of speakers. To this end, we leverage a neural network training scheme called Graph-PIT proposed recently for neural source separation. Experiments with simulated active-meeting-like data and CALLHOME data show the superiority of the proposed approach over the conventional methods. author: - first_name: Keisuke full_name: Kinoshita, Keisuke last_name: Kinoshita - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Marc full_name: Delcroix, Marc last_name: Delcroix - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Kinoshita K, von Neumann T, Delcroix M, Boeddeker C, Haeb-Umbach R. Utterance-by-utterance overlap-aware neural diarization with Graph-PIT. In: Proc. Interspeech 2022. ISCA; 2022:1486-1490. doi:10.21437/Interspeech.2022-11408' apa: Kinoshita, K., von Neumann, T., Delcroix, M., Boeddeker, C., & Haeb-Umbach, R. (2022). Utterance-by-utterance overlap-aware neural diarization with Graph-PIT. Proc. Interspeech 2022, 1486–1490. https://doi.org/10.21437/Interspeech.2022-11408 bibtex: '@inproceedings{Kinoshita_von Neumann_Delcroix_Boeddeker_Haeb-Umbach_2022, title={Utterance-by-utterance overlap-aware neural diarization with Graph-PIT}, DOI={10.21437/Interspeech.2022-11408}, booktitle={Proc. Interspeech 2022}, publisher={ISCA}, author={Kinoshita, Keisuke and von Neumann, Thilo and Delcroix, Marc and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2022}, pages={1486–1490} }' chicago: Kinoshita, Keisuke, Thilo von Neumann, Marc Delcroix, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Utterance-by-Utterance Overlap-Aware Neural Diarization with Graph-PIT.” In Proc. Interspeech 2022, 1486–90. ISCA, 2022. https://doi.org/10.21437/Interspeech.2022-11408. ieee: 'K. Kinoshita, T. von Neumann, M. Delcroix, C. Boeddeker, and R. Haeb-Umbach, “Utterance-by-utterance overlap-aware neural diarization with Graph-PIT,” in Proc. Interspeech 2022, 2022, pp. 1486–1490, doi: 10.21437/Interspeech.2022-11408.' mla: Kinoshita, Keisuke, et al. “Utterance-by-Utterance Overlap-Aware Neural Diarization with Graph-PIT.” Proc. Interspeech 2022, ISCA, 2022, pp. 1486–90, doi:10.21437/Interspeech.2022-11408. short: 'K. Kinoshita, T. von Neumann, M. Delcroix, C. Boeddeker, R. Haeb-Umbach, in: Proc. Interspeech 2022, ISCA, 2022, pp. 1486–1490.' conference: name: Interspeech 2022 date_created: 2022-10-28T12:07:57Z date_updated: 2023-11-15T12:17:04Z department: - _id: '54' doi: 10.21437/Interspeech.2022-11408 language: - iso: eng page: 1486-1490 publication: Proc. Interspeech 2022 publication_status: published publisher: ISCA quality_controlled: '1' status: public title: Utterance-by-utterance overlap-aware neural diarization with Graph-PIT type: conference user_id: '49870' year: '2022' ... --- _id: '33819' author: - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Keisuke full_name: Kinoshita, Keisuke last_name: Kinoshita - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Marc full_name: Delcroix, Marc last_name: Delcroix - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach 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: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2022. doi:10.1109/icassp43922.2022.9746757' apa: 'von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2022). SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9746757' bibtex: '@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2022, title={SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}, DOI={10.1109/icassp43922.2022.9746757}, 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} }' 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 ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022. https://doi.org/10.1109/icassp43922.2022.9746757.' 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: 10.1109/icassp43922.2022.9746757.' mla: 'von Neumann, Thilo, et al. “SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.” ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022, doi:10.1109/icassp43922.2022.9746757.' 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.' date_created: 2022-10-20T05:29:12Z date_updated: 2023-11-15T12:16:47Z ddc: - '000' department: - _id: '54' doi: 10.1109/icassp43922.2022.9746757 file: - access_level: open_access content_type: application/pdf creator: tvn date_created: 2022-10-20T05:33:10Z date_updated: 2022-10-20T05:33:10Z file_id: '33820' file_name: main.pdf file_size: 228069 relation: main_file - access_level: open_access content_type: application/pdf creator: tvn date_created: 2022-10-20T05:35:32Z date_updated: 2022-10-20T05:35:32Z file_id: '33821' file_name: poster.pdf file_size: 229166 relation: poster file_date_updated: 2022-10-20T05:35:32Z has_accepted_license: '1' language: - iso: eng oa: '1' project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) publication_status: published publisher: IEEE quality_controlled: '1' related_material: link: - relation: supplementary_material url: https://github.com/fgnt/graph_pit status: public title: 'SA-SDR: A Novel Loss Function for Separation of Meeting Style Data' type: conference user_id: '49870' year: '2022' ... --- _id: '33847' abstract: - lang: eng 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." author: - first_name: Tobias full_name: Cord-Landwehr, Tobias id: '44393' last_name: Cord-Landwehr - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: ama: 'Cord-Landwehr T, von Neumann T, Boeddeker C, Haeb-Umbach R. MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. In: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). ; 2022.' apa: 'Cord-Landwehr, T., von Neumann, T., Boeddeker, C., & Haeb-Umbach, R. (2022). MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). 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} }' chicago: 'Cord-Landwehr, Tobias, Thilo von Neumann, Christoph Boeddeker, and Reinhold Haeb-Umbach. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.” In 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 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.' mla: 'Cord-Landwehr, Tobias, et al. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.” 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.' short: 'T. Cord-Landwehr, T. von Neumann, C. Boeddeker, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.' conference: location: Bamberg name: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC) date_created: 2022-10-20T14:02:14Z date_updated: 2023-11-15T14:55:14Z ddc: - '000' department: - _id: '54' external_id: arxiv: - '2209.11494' file: - access_level: open_access content_type: application/pdf creator: cord date_created: 2023-11-15T14:54:56Z date_updated: 2023-11-15T14:54:56Z file_id: '48931' file_name: mms_msg_camera_ready.pdf file_size: 177975 relation: main_file file_date_updated: 2023-11-15T14:54:56Z has_accepted_license: '1' language: - iso: eng oa: '1' project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC) quality_controlled: '1' status: public title: 'MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator' type: conference user_id: '44393' year: '2022' ... --- _id: '33848' 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." author: - first_name: Tobias full_name: Cord-Landwehr, Tobias id: '44393' last_name: Cord-Landwehr - first_name: Christoph full_name: Boeddeker, Christoph id: '40767' last_name: Boeddeker - first_name: Thilo full_name: von Neumann, Thilo id: '49870' last_name: von Neumann orcid: https://orcid.org/0000-0002-7717-8670 - first_name: Catalin full_name: Zorila, Catalin last_name: Zorila - first_name: Rama full_name: Doddipatla, Rama last_name: Doddipatla - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach citation: 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: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). IEEE; 2022.' apa: 'Cord-Landwehr, T., Boeddeker, C., von Neumann, T., Zorila, C., Doddipatla, R., & Haeb-Umbach, R. (2022). Monaural source separation: From anechoic to reverberant environments. 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). 2022 International Workshop on Acoustic Signal Enhancement (IWAENC).' 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} }' 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 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). Bamberg: 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.' mla: 'Cord-Landwehr, Tobias, et al. “Monaural Source Separation: From Anechoic to Reverberant Environments.” 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, 2022.' short: 'T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla, R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), IEEE, Bamberg, 2022.' conference: name: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC) date_created: 2022-10-20T14:07:28Z date_updated: 2023-11-15T14:53:06Z ddc: - '000' department: - _id: '54' external_id: arxiv: - '2111.07578' file: - access_level: open_access content_type: application/pdf creator: cord date_created: 2023-11-15T14:52:16Z date_updated: 2023-11-15T14:52:16Z file_id: '48930' file_name: monaural_source_separation.pdf file_size: 212890 relation: main_file file_date_updated: 2023-11-15T14:52:16Z has_accepted_license: '1' language: - iso: eng oa: '1' place: Bamberg project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC) publisher: IEEE status: public title: 'Monaural source separation: From anechoic to reverberant environments' type: conference user_id: '44393' year: '2022' ...