Please note that LibreCat no longer supports Internet Explorer versions 8 or 9 (or earlier).
We recommend upgrading to the latest Internet Explorer, Google Chrome, or Firefox.
333 Publications
2025 | Conference Paper | LibreCat-ID: 59900
@inproceedings{Werning_Häb-Umbach_2025, place={Copenhagen}, title={Distilling Efficient Audio Models using Data Pruning with CLAP}, DOI={10.71568/DASDAGA2025.149}, booktitle={Proceedings of DAS|DAGA 2025}, author={Werning, Alexander and Häb-Umbach, Reinhold}, editor={Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025}, year={2025} }
LibreCat
| DOI
2025 | Conference Paper | LibreCat-ID: 59999
@inproceedings{Rautenberg_Kuhlmann_Seebauer_Wiechmann_Wagner_Haeb-Umbach_2025, title={Speech Synthesis along Perceptual Voice Quality Dimensions}, DOI={10.1109/icassp49660.2025.10888012}, booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Rautenberg, Frederik and Kuhlmann, Michael and Seebauer, Fritz and Wiechmann, Jana and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2025} }
LibreCat
| DOI
2024 | Preprint | LibreCat-ID: 56273 | 
@article{Cornell_Park_Huang_Boeddeker_Chang_Maciejewski_Wiesner_Garcia_Watanabe_2024, title={The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization}, journal={arXiv:2407.16447}, author={Cornell, Samuele and Park, Taejin and Huang, Steve and Boeddeker, Christoph and Chang, Xuankai and Maciejewski, Matthew and Wiesner, Matthew and Garcia, Paola and Watanabe, Shinji}, year={2024} }
LibreCat
| Download (ext.)
| arXiv
2024 | Conference Paper | LibreCat-ID: 57031 |
@inproceedings{Gburrek_Meise_Schmalenstroeer_Haeb-Umbach_2024, title={Diminishing Domain Mismatch for DNN-Based Acoustic Distance Estimation via Stochastic Room Reverberation Models}, DOI={10.1109/iwaenc61483.2024.10694103}, booktitle={2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Gburrek, Tobias and Meise, Adrian and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
| Files available
| DOI
2024 | Journal Article | LibreCat-ID: 52958 |
@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} }
LibreCat
| Files available
| DOI
| Download (ext.)
2024 | Conference Paper | LibreCat-ID: 57085 |
@inproceedings{Cord-Landwehr_Boeddeker_Haeb-Umbach_2024, title={Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models}, DOI={10.1109/ICASSP49660.2025.10888445}, booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
| DOI
| Download (ext.)
2024 | Report | LibreCat-ID: 57161
@book{Werning_Haeb-Umbach_2024, title={UPB-NT submission to DCASE24: Dataset pruning for targeted knowledge distillation}, author={Werning, Alexander and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
2024 | Conference Paper | LibreCat-ID: 57160
@inproceedings{Werning_Haeb-Umbach_2024, title={Target-Specific Dataset Pruning for Compression of Audio Tagging Models}, booktitle={32nd European Signal Processing Conference (EUSIPCO 2024)}, author={Werning, Alexander and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
| Files available
2024 | Conference Paper | LibreCat-ID: 57099
@inproceedings{Xie_Kuhlmann_Rautenberg_Tan_Häb-Umbach_2024, title={Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder}, booktitle={2024 32nd European Signal Processing Conference (EUSIPCO)}, author={Xie, Yuying and Kuhlmann, Michael and Rautenberg, Frederik and Tan, Zheng-Hua and Häb-Umbach, Reinhold}, year={2024}, pages={436–440} }
LibreCat
2024 | Conference Paper | LibreCat-ID: 56004 |
@inproceedings{von Neumann_Boeddeker_Cord-Landwehr_Delcroix_Haeb-Umbach_2024, title={Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization}, DOI={10.1109/icasspw62465.2024.10625894}, booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, publisher={IEEE}, author={von Neumann, Thilo and Boeddeker, Christoph and Cord-Landwehr, Tobias and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
| Files available
| DOI
2024 | Conference Paper | LibreCat-ID: 53659
@inproceedings{Cord-Landwehr_Boeddeker_Zorilă_Doddipatla_Haeb-Umbach_2024, title={Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios}, DOI={10.1109/icassp48485.2024.10445911}, booktitle={ICASSP 2024 - 2024 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={2024} }
LibreCat
| DOI
2024 | Conference Paper | LibreCat-ID: 56272 |
@inproceedings{Boeddeker_Cord-Landwehr_Haeb-Umbach_2024, title={Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment}, DOI={10.21437/interspeech.2024-1286}, booktitle={Interspeech 2024}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
| DOI
| Download (ext.)
2024 | Conference Paper | LibreCat-ID: 57659 |
@inproceedings{Vieting_Berger_von Neumann_Boeddeker_Schlüter_Haeb-Umbach_2024, title={Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription}, booktitle={2024 IEEE Spoken Language Technology Workshop (SLT)}, author={Vieting, Peter and Berger, Simon and von Neumann, Thilo and Boeddeker, Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2024} }
LibreCat
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 48269 |
@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} }
LibreCat
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 48270 |
@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} }
LibreCat
| Files available
2023 | Conference Paper | LibreCat-ID: 48355 |
@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} }
LibreCat
| Files available
| Download (ext.)
| arXiv
2023 | Conference Paper | LibreCat-ID: 48410 |
@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} }
LibreCat
| Files available
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 48391
@inproceedings{Aralikatti_Boeddeker_Wichern_Subramanian_Le Roux_2023, title={Reverberation as Supervision For Speech Separation}, DOI={10.1109/icassp49357.2023.10095022}, booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Aralikatti, Rohith and Boeddeker, Christoph and Wichern, Gordon and Subramanian, Aswin and Le Roux, Jonathan}, year={2023} }
LibreCat
| DOI
2023 | Conference Paper | LibreCat-ID: 46069
@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} }
LibreCat
2023 | Journal Article | LibreCat-ID: 35602 |
@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} }
LibreCat
| Files available
| DOI
2023 | Conference Paper | LibreCat-ID: 49109 |
@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} }
LibreCat
| Files available
2023 | Conference Paper | LibreCat-ID: 44849 |
@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} }
LibreCat
| Files available
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 49111
@inproceedings{Ebbers_Haeb-Umbach_Serizel_2023, place={Tampere, Finland}, title={Post-Processing Independent Evaluation of Sound Event Detection Systems}, booktitle={Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}, year={2023}, pages={36–40} }
LibreCat
| Files available
2023 | Conference Paper | LibreCat-ID: 57098
@inproceedings{Seebauer_Kuhlmann_Häb-Umbach_Wagner_2023, title={DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH}, booktitle={Proceedings of the 20th International Congress of Phonetic Sciences}, author={Seebauer, Fritz and Kuhlmann, Michael and Häb-Umbach, Reinhold and Wagner, Petra}, year={2023} }
LibreCat
2023 | Conference Paper | LibreCat-ID: 57086
@inproceedings{Kuhlmann_Meise_Seebauer_Wagner_Häb-Umbach_2023, title={Investigating Speaker Embedding Disentanglement on Natural Read Speech}, booktitle={Speech Communication; 15th ITG Conference}, author={Kuhlmann, Michael and Meise, Adrian and Seebauer, Fritz and Wagner, Petra and Häb-Umbach, Reinhold}, year={2023}, pages={121–125} }
LibreCat
2023 | Conference Paper | LibreCat-ID: 48281 |
@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} }
LibreCat
| Files available
| DOI
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 48275 |
@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} }
LibreCat
| Files available
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 47128 |
@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} }
LibreCat
| Files available
| DOI
2023 | Conference Paper | LibreCat-ID: 47129 |
@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} }
LibreCat
| Files available
| DOI
2023 | Conference Paper | LibreCat-ID: 54439 |
@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2023, title={Multi-stage diarization refinement for the CHiME-7 DASR scenario}, DOI={10.21437/chime.2023-10}, booktitle={7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2023} }
LibreCat
| DOI
| Download (ext.)
2023 | Conference Paper | LibreCat-ID: 48390 |
@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} }
LibreCat
| DOI
| Download (ext.)
2022 | Journal Article | LibreCat-ID: 33669 |
@article{Zhang_Chang_Boeddeker_Nakatani_Watanabe_Qian_2022, title={End-to-End Dereverberation, Beamforming, and Speech Recognition in A Cocktail Party}, DOI={10.1109/TASLP.2022.3209942}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, author={Zhang, Wangyou and Chang, Xuankai and Boeddeker, Christoph and Nakatani, Tomohiro and Watanabe, Shinji and Qian, Yanmin}, year={2022} }
LibreCat
| Files available
| DOI
2022 | Conference Paper | LibreCat-ID: 33471
@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} }
LibreCat
| Files available
2022 | Conference Paper | LibreCat-ID: 33806
@inproceedings{Afifi_Karl_Gburrek_Schmalenstroeer_2022, title={Data-driven Time Synchronization in Wireless Multimedia Networks}, DOI={10.1109/iwcmc55113.2022.9824980}, booktitle={2022 International Wireless Communications and Mobile Computing (IWCMC)}, publisher={IEEE}, author={Afifi, Haitham and Karl, Holger and Gburrek, Tobias and Schmalenstroeer, Joerg}, year={2022} }
LibreCat
| DOI
2022 | Conference Paper | LibreCat-ID: 33847 |
@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} }
LibreCat
| Files available
| arXiv
2022 | Conference Paper | LibreCat-ID: 33807 |
@inproceedings{Gburrek_Schmalenstroeer_Haeb-Umbach_2022, title={On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes}, DOI={10.1109/icassp43922.2022.9746284}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher={IEEE}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2022} }
LibreCat
| Files available
| DOI
2022 | Journal Article | LibreCat-ID: 33451 |
@article{Grimm_Fei_Warsitz_Farhoud_Breddermann_Haeb-Umbach_2022, title={Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications}, volume={71}, DOI={10.1109/TVT.2022.3182411}, number={9}, journal={IEEE Transactions on Vehicular Technology}, author={Grimm, Christopher and Fei, Tai and Warsitz, Ernst and Farhoud, Ridha and Breddermann, Tobias and Haeb-Umbach, Reinhold}, year={2022}, pages={9435–9449} }
LibreCat
| Files available
| DOI
2022 | Conference Paper | LibreCat-ID: 33696 |
@inproceedings{Wiechmann_Glarner_Rautenberg_Wagner_Haeb-Umbach_2022, title={Technically enabled explaining of voice characteristics}, booktitle={18. Phonetik und Phonologie im deutschsprachigen Raum (P&P)}, author={Wiechmann, Jana and Glarner, Thomas and Rautenberg, Frederik and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022} }
LibreCat
| Files available
2022 | Conference Paper | LibreCat-ID: 33857 |
@inproceedings{Kuhlmann_Seebauer_Ebbers_Wagner_Haeb-Umbach_2022, title={Investigation into Target Speaking Rate Adaptation for Voice Conversion}, DOI={10.21437/interspeech.2022-10740}, booktitle={Interspeech 2022}, publisher={ISCA}, author={Kuhlmann, Michael and Seebauer, Fritz and Ebbers, Janek and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022} }
LibreCat
| Files available
| DOI
| Download (ext.)
2022 | Conference Paper | LibreCat-ID: 33808 |
@inproceedings{Gburrek_Schmalenstroeer_Heitkaemper_Haeb-Umbach_2022, title={Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription}, DOI={10.1109/IWAENC53105.2022.9914772}, booktitle={2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}, publisher={IEEE}, author={Gburrek, Tobias and Schmalenstroeer, Joerg and Heitkaemper, Jens and Haeb-Umbach, Reinhold}, year={2022} }
LibreCat
| Files available
| DOI
2022 | Conference Paper | LibreCat-ID: 34072 |
@inproceedings{Ebbers_Haeb-Umbach_Serizel_2022, title={Threshold Independent Evaluation of Sound Event Detection Scores}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}, year={2022} }
LibreCat
| Files available
2022 | Report | LibreCat-ID: 49113
@book{Ebbers_Haeb-Umbach_2022, title={Pre-Training And Self-Training For Sound Event Detection In Domestic Environments}, author={Ebbers, Janek and Haeb-Umbach, Reinhold}, year={2022} }
LibreCat
| Files available
2022 | Conference Paper | LibreCat-ID: 33848 |
@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} }
LibreCat
| Files available
| arXiv
2022 | Conference Paper | LibreCat-ID: 33819 |
@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} }
LibreCat
| Files available
| DOI
2022 | Misc | LibreCat-ID: 33816 |
@book{Gburrek_Boeddeker_von Neumann_Cord-Landwehr_Schmalenstroeer_Haeb-Umbach_2022, title={A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network}, DOI={10.48550/ARXIV.2205.00944}, publisher={arXiv}, author={Gburrek, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Cord-Landwehr, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2022} }
LibreCat
| Files available
| DOI
2022 | Conference Paper | LibreCat-ID: 33954 |
@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} }
LibreCat
| DOI
| Download (ext.)
2022 | Conference Paper | LibreCat-ID: 33958
@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} }
LibreCat
| DOI
| Download (ext.)
2021 | Journal Article | LibreCat-ID: 21065 |
@article{Haeb-Umbach_Heymann_Drude_Watanabe_Delcroix_Nakatani_2021, title={Far-Field Automatic Speech Recognition}, volume={109}, DOI={10.1109/JPROC.2020.3018668}, number={2}, journal={Proceedings of the IEEE}, author={Haeb-Umbach, Reinhold and Heymann, Jahn and Drude, Lukas and Watanabe, Shinji and Delcroix, Marc and Nakatani, Tomohiro}, year={2021}, pages={124–148} }
LibreCat
| Files available
| DOI
2021 | Conference Paper | LibreCat-ID: 28256
@inproceedings{Zhang_Boeddeker_Watanabe_Nakatani_Delcroix_Kinoshita_Ochiai_Kamo_Haeb-Umbach_Qian_2021, title={End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend}, DOI={10.1109/icassp39728.2021.9414464}, booktitle={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Zhang, Wangyou and Boeddeker, Christoph and Watanabe, Shinji and Nakatani, Tomohiro and Delcroix, Marc and Kinoshita, Keisuke and Ochiai, Tsubasa and Kamo, Naoyuki and Haeb-Umbach, Reinhold and Qian, Yanmin}, year={2021} }
LibreCat
| DOI
2021 | Conference Paper | LibreCat-ID: 28262
@inproceedings{Li_Shi_Zhang_Subramanian_Chang_Kamo_Hira_Hayashi_Boeddeker_Chen_et al._2021, title={ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for ASR Integration}, DOI={10.1109/slt48900.2021.9383615}, booktitle={2021 IEEE Spoken Language Technology Workshop (SLT)}, author={Li, Chenda and Shi, Jing and Zhang, Wangyou and Subramanian, Aswin Shanmugam and Chang, Xuankai and Kamo, Naoyuki and Hira, Moto and Hayashi, Tomoki and Boeddeker, Christoph and Chen, Zhuo and et al.}, year={2021} }
LibreCat
| DOI