[{"citation":{"bibtex":"@inproceedings{Rautenberg_Kuhlmann_Seebauer_Wiechmann_Wagner_Haeb-Umbach_2025, title={Speech Synthesis along Perceptual Voice Quality Dimensions}, DOI={<a href=\"https://doi.org/10.1109/icassp49660.2025.10888012\">10.1109/icassp49660.2025.10888012</a>}, 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} }","short":"F. Rautenberg, M. Kuhlmann, F. Seebauer, J. Wiechmann, P. Wagner, R. Haeb-Umbach, in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2025.","mla":"Rautenberg, Frederik, et al. “Speech Synthesis along Perceptual Voice Quality Dimensions.” <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, IEEE, 2025, doi:<a href=\"https://doi.org/10.1109/icassp49660.2025.10888012\">10.1109/icassp49660.2025.10888012</a>.","apa":"Rautenberg, F., Kuhlmann, M., Seebauer, F., Wiechmann, J., Wagner, P., &#38; Haeb-Umbach, R. (2025). Speech Synthesis along Perceptual Voice Quality Dimensions. <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India . <a href=\"https://doi.org/10.1109/icassp49660.2025.10888012\">https://doi.org/10.1109/icassp49660.2025.10888012</a>","ieee":"F. Rautenberg, M. Kuhlmann, F. Seebauer, J. Wiechmann, P. Wagner, and R. Haeb-Umbach, “Speech Synthesis along Perceptual Voice Quality Dimensions,” presented at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India , 2025, doi: <a href=\"https://doi.org/10.1109/icassp49660.2025.10888012\">10.1109/icassp49660.2025.10888012</a>.","chicago":"Rautenberg, Frederik, Michael Kuhlmann, Fritz Seebauer, Jana Wiechmann, Petra Wagner, and Reinhold Haeb-Umbach. “Speech Synthesis along Perceptual Voice Quality Dimensions.” In <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE, 2025. <a href=\"https://doi.org/10.1109/icassp49660.2025.10888012\">https://doi.org/10.1109/icassp49660.2025.10888012</a>.","ama":"Rautenberg F, Kuhlmann M, Seebauer F, Wiechmann J, Wagner P, Haeb-Umbach R. Speech Synthesis along Perceptual Voice Quality Dimensions. In: <i>ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2025. doi:<a href=\"https://doi.org/10.1109/icassp49660.2025.10888012\">10.1109/icassp49660.2025.10888012</a>"},"year":"2025","publication_status":"published","doi":"10.1109/icassp49660.2025.10888012","conference":{"location":"Hyderabad, India ","end_date":"2025-04-11","start_date":"2025-04-06","name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},"title":"Speech Synthesis along Perceptual Voice Quality Dimensions","date_created":"2025-05-20T08:17:22Z","author":[{"first_name":"Frederik","last_name":"Rautenberg","id":"72602","full_name":"Rautenberg, Frederik"},{"first_name":"Michael","id":"49871","full_name":"Kuhlmann, Michael","last_name":"Kuhlmann"},{"full_name":"Seebauer, Fritz","last_name":"Seebauer","first_name":"Fritz"},{"last_name":"Wiechmann","full_name":"Wiechmann, Jana","first_name":"Jana"},{"last_name":"Wagner","full_name":"Wagner, Petra","first_name":"Petra"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_updated":"2025-05-26T11:09:56Z","publisher":"IEEE","status":"public","type":"conference","publication":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","language":[{"iso":"eng"}],"user_id":"72602","department":[{"_id":"54"},{"_id":"660"}],"project":[{"grant_number":"438445824","name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","_id":"129"}],"_id":"59999"},{"title":"Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice","doi":"10.21437/Interspeech.2025-1443","conference":{"location":"Rotterdam","end_date":"2025-08-21","start_date":"2025-08-17","name":"Interspeech"},"publisher":"ISCA","date_updated":"2025-08-28T08:56:49Z","author":[{"first_name":"Frederik","last_name":"Rautenberg","full_name":"Rautenberg, Frederik","id":"72602"},{"full_name":"Seebauer, Fritz","last_name":"Seebauer","first_name":"Fritz"},{"first_name":"Jana","full_name":"Wiechmann, Jana","last_name":"Wiechmann"},{"id":"49871","full_name":"Kuhlmann, Michael","last_name":"Kuhlmann","first_name":"Michael"},{"last_name":"Wagner","full_name":"Wagner, Petra","first_name":"Petra"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_created":"2025-08-28T08:39:01Z","year":"2025","citation":{"bibtex":"@inproceedings{Rautenberg_Seebauer_Wiechmann_Kuhlmann_Wagner_Haeb-Umbach_2025, title={Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice}, DOI={<a href=\"https://doi.org/10.21437/Interspeech.2025-1443\">10.21437/Interspeech.2025-1443</a>}, booktitle={Interspeech 2025}, publisher={ISCA}, author={Rautenberg, Frederik and Seebauer, Fritz and Wiechmann, Jana and Kuhlmann, Michael and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2025} }","mla":"Rautenberg, Frederik, et al. “Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice.” <i>Interspeech 2025</i>, ISCA, 2025, doi:<a href=\"https://doi.org/10.21437/Interspeech.2025-1443\">10.21437/Interspeech.2025-1443</a>.","short":"F. Rautenberg, F. Seebauer, J. Wiechmann, M. Kuhlmann, P. Wagner, R. Haeb-Umbach, in: Interspeech 2025, ISCA, 2025.","apa":"Rautenberg, F., Seebauer, F., Wiechmann, J., Kuhlmann, M., Wagner, P., &#38; Haeb-Umbach, R. (2025). Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice. <i>Interspeech 2025</i>. Interspeech, Rotterdam. <a href=\"https://doi.org/10.21437/Interspeech.2025-1443\">https://doi.org/10.21437/Interspeech.2025-1443</a>","ama":"Rautenberg F, Seebauer F, Wiechmann J, Kuhlmann M, Wagner P, Haeb-Umbach R. Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice. In: <i>Interspeech 2025</i>. ISCA; 2025. doi:<a href=\"https://doi.org/10.21437/Interspeech.2025-1443\">10.21437/Interspeech.2025-1443</a>","chicago":"Rautenberg, Frederik, Fritz Seebauer, Jana Wiechmann, Michael Kuhlmann, Petra Wagner, and Reinhold Haeb-Umbach. “Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice.” In <i>Interspeech 2025</i>. ISCA, 2025. <a href=\"https://doi.org/10.21437/Interspeech.2025-1443\">https://doi.org/10.21437/Interspeech.2025-1443</a>.","ieee":"F. Rautenberg, F. Seebauer, J. Wiechmann, M. Kuhlmann, P. Wagner, and R. Haeb-Umbach, “Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice,” presented at the Interspeech, Rotterdam, 2025, doi: <a href=\"https://doi.org/10.21437/Interspeech.2025-1443\">10.21437/Interspeech.2025-1443</a>."},"language":[{"iso":"eng"}],"project":[{"_id":"129","name":"TRR 318; TP C06: Technisch unterstütztes Erklären von Stimmcharakteristika"}],"_id":"61047","user_id":"72602","department":[{"_id":"54"},{"_id":"660"}],"status":"public","type":"conference","publication":"Interspeech 2025"},{"status":"public","publication":"2024 32nd European Signal Processing Conference (EUSIPCO)","type":"conference","language":[{"iso":"eng"}],"_id":"57099","department":[{"_id":"54"}],"user_id":"49871","year":"2024","page":"436–440","citation":{"apa":"Xie, Y., Kuhlmann, M., Rautenberg, F., Tan, Z.-H., &#38; Häb-Umbach, R. (2024). Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder. <i>2024 32nd European Signal Processing Conference (EUSIPCO)</i>, 436–440.","bibtex":"@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} }","mla":"Xie, Yuying, et al. “Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder.” <i>2024 32nd European Signal Processing Conference (EUSIPCO)</i>, 2024, pp. 436–440.","short":"Y. Xie, M. Kuhlmann, F. Rautenberg, Z.-H. Tan, R. Häb-Umbach, in: 2024 32nd European Signal Processing Conference (EUSIPCO), 2024, pp. 436–440.","ieee":"Y. Xie, M. Kuhlmann, F. Rautenberg, Z.-H. Tan, and R. Häb-Umbach, “Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder,” in <i>2024 32nd European Signal Processing Conference (EUSIPCO)</i>, 2024, pp. 436–440.","chicago":"Xie, Yuying, Michael Kuhlmann, Frederik Rautenberg, Zheng-Hua Tan, and Reinhold Häb-Umbach. “Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder.” In <i>2024 32nd European Signal Processing Conference (EUSIPCO)</i>, 436–440, 2024.","ama":"Xie Y, Kuhlmann M, Rautenberg F, Tan Z-H, Häb-Umbach R. Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder. In: <i>2024 32nd European Signal Processing Conference (EUSIPCO)</i>. ; 2024:436–440."},"title":"Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder","date_updated":"2024-11-15T06:54:40Z","author":[{"first_name":"Yuying","last_name":"Xie","full_name":"Xie, Yuying"},{"full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann","first_name":"Michael"},{"first_name":"Frederik","last_name":"Rautenberg","full_name":"Rautenberg, Frederik","id":"72602"},{"last_name":"Tan","full_name":"Tan, Zheng-Hua","first_name":"Zheng-Hua"},{"full_name":"Häb-Umbach, Reinhold","id":"242","last_name":"Häb-Umbach","first_name":"Reinhold"}],"date_created":"2024-11-15T06:52:54Z"},{"publication":"ITG Conference on Speech Communication","file":[{"content_type":"application/pdf","relation":"main_file","success":1,"creator":"frra","date_created":"2023-10-20T08:20:58Z","date_updated":"2023-10-20T08:20:58Z","access_level":"closed","file_id":"48359","file_name":"arxiv.pdf","file_size":272390}],"abstract":[{"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.","lang":"eng"}],"external_id":{"arxiv":["2310.12599"]},"language":[{"iso":"eng"}],"ddc":["000"],"year":"2023","date_created":"2023-10-20T08:04:46Z","title":"On Feature Importance and Interpretability of Speaker Representations","type":"conference","status":"public","user_id":"72602","department":[{"_id":"54"},{"_id":"660"}],"project":[{"_id":"129","name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","grant_number":"438445824"}],"_id":"48355","file_date_updated":"2023-10-20T08:20:58Z","has_accepted_license":"1","citation":{"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} }","mla":"Rautenberg, Frederik, et al. “On Feature Importance and Interpretability of Speaker Representations.” <i>ITG Conference on Speech Communication</i>, 2023.","short":"F. Rautenberg, M. Kuhlmann, J. Wiechmann, F. Seebauer, P. Wagner, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2023.","apa":"Rautenberg, F., Kuhlmann, M., Wiechmann, J., Seebauer, F., Wagner, P., &#38; Haeb-Umbach, R. (2023). On Feature Importance and Interpretability of Speaker Representations. <i>ITG Conference on Speech Communication</i>. ITG Conference on Speech Communication, Aachen.","ama":"Rautenberg F, Kuhlmann M, Wiechmann J, Seebauer F, Wagner P, Haeb-Umbach R. On Feature Importance and Interpretability of Speaker Representations. In: <i>ITG Conference on Speech Communication</i>. ; 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 <i>ITG Conference on Speech Communication</i>, 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."},"author":[{"first_name":"Frederik","full_name":"Rautenberg, Frederik","id":"72602","last_name":"Rautenberg"},{"last_name":"Kuhlmann","full_name":"Kuhlmann, Michael","id":"49871","first_name":"Michael"},{"first_name":"Jana","full_name":"Wiechmann, Jana","last_name":"Wiechmann"},{"first_name":"Fritz","full_name":"Seebauer, Fritz","last_name":"Seebauer"},{"full_name":"Wagner, Petra","last_name":"Wagner","first_name":"Petra"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"oa":"1","date_updated":"2023-11-22T13:44:33Z","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2310.12599"}],"conference":{"end_date":"2023-09-22","location":"Aachen","name":"ITG Conference on Speech Communication","start_date":"2023-09-20"}},{"publication":"20th International Congress of the Phonetic Sciences (ICPhS) ","type":"conference","status":"public","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","access_level":"closed","file_id":"48413","file_name":"188.pdf","file_size":209980,"creator":"frra","date_created":"2023-10-24T08:03:27Z","date_updated":"2023-10-24T08:03:27Z"}],"department":[{"_id":"54"},{"_id":"660"}],"user_id":"72602","_id":"48410","project":[{"_id":"129","name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","grant_number":"438445824"}],"language":[{"iso":"eng"}],"file_date_updated":"2023-10-24T08:03:27Z","ddc":["040"],"has_accepted_license":"1","citation":{"apa":"Wiechmann, J., Rautenberg, F., Wagner, P., &#38; Haeb-Umbach, R. (2023). Explaining voice characteristics to novice voice practitioners-How successful is it? <i>20th International Congress of the Phonetic Sciences (ICPhS) </i>.","short":"J. Wiechmann, F. Rautenberg, P. Wagner, R. Haeb-Umbach, in: 20th International Congress of the Phonetic Sciences (ICPhS) , 2023.","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} }","mla":"Wiechmann, Jana, et al. “Explaining Voice Characteristics to Novice Voice Practitioners-How Successful Is It?” <i>20th International Congress of the Phonetic Sciences (ICPhS) </i>, 2023.","ama":"Wiechmann J, Rautenberg F, Wagner P, Haeb-Umbach R. Explaining voice characteristics to novice voice practitioners-How successful is it? In: <i>20th International Congress of the Phonetic Sciences (ICPhS) </i>. ; 2023.","ieee":"J. Wiechmann, F. Rautenberg, P. Wagner, and R. Haeb-Umbach, “Explaining voice characteristics to novice voice practitioners-How successful is it?,” 2023.","chicago":"Wiechmann, Jana, Frederik Rautenberg, Petra Wagner, and Reinhold Haeb-Umbach. “Explaining Voice Characteristics to Novice Voice Practitioners-How Successful Is It?” In <i>20th International Congress of the Phonetic Sciences (ICPhS) </i>, 2023."},"year":"2023","author":[{"full_name":"Wiechmann, Jana","last_name":"Wiechmann","first_name":"Jana"},{"last_name":"Rautenberg","full_name":"Rautenberg, Frederik","id":"72602","first_name":"Frederik"},{"first_name":"Petra","full_name":"Wagner, Petra","last_name":"Wagner"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2023-10-24T08:05:40Z","oa":"1","date_updated":"2023-11-22T13:44:59Z","conference":{"start_date":"2023-08-07","end_date":"2023-08-11"},"main_file_link":[{"open_access":"1"}],"title":"Explaining voice characteristics to novice voice practitioners-How successful is it?"},{"title":"Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics","conference":{"location":"Hamburg","end_date":"2023-03-09","start_date":"2023-03-06","name":"DAGA 2023 - 49. Jahrestagung für Akustik"},"main_file_link":[{"url":"https://pub.dega-akustik.de/DAGA_2023/data/articles/000105.pdf","open_access":"1"}],"date_updated":"2024-02-29T17:05:16Z","oa":"1","date_created":"2023-05-15T08:48:54Z","author":[{"full_name":"Rautenberg, Frederik","id":"72602","last_name":"Rautenberg","first_name":"Frederik"},{"first_name":"Michael","last_name":"Kuhlmann","full_name":"Kuhlmann, Michael","id":"49871"},{"first_name":"Janek","last_name":"Ebbers","full_name":"Ebbers, Janek","id":"34851"},{"first_name":"Jana","full_name":"Wiechmann, Jana","last_name":"Wiechmann"},{"last_name":"Seebauer","full_name":"Seebauer, Fritz","first_name":"Fritz"},{"first_name":"Petra","last_name":"Wagner","full_name":"Wagner, Petra"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"year":"2023","page":"1409-1412","citation":{"ama":"Rautenberg F, Kuhlmann M, Ebbers J, et al. Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics. In: <i>Fortschritte Der Akustik - DAGA 2023</i>. ; 2023:1409-1412.","ieee":"F. Rautenberg <i>et al.</i>, “Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics,” in <i>Fortschritte der Akustik - DAGA 2023</i>, Hamburg, 2023, pp. 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 <i>Fortschritte Der Akustik - DAGA 2023</i>, 1409–12, 2023.","apa":"Rautenberg, F., Kuhlmann, M., Ebbers, J., Wiechmann, J., Seebauer, F., Wagner, P., &#38; Haeb-Umbach, R. (2023). Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics. <i>Fortschritte Der Akustik - DAGA 2023</i>, 1409–1412.","mla":"Rautenberg, Frederik, et al. “Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics.” <i>Fortschritte Der Akustik - DAGA 2023</i>, 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.","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} }"},"has_accepted_license":"1","publication_status":"published","ddc":["000"],"file_date_updated":"2024-02-29T16:15:12Z","language":[{"iso":"eng"}],"_id":"44849","project":[{"grant_number":"438445824","_id":"129","name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)"}],"department":[{"_id":"54"},{"_id":"660"}],"user_id":"72602","status":"public","file":[{"content_type":"application/pdf","relation":"main_file","date_updated":"2024-02-29T16:15:12Z","creator":"frra","date_created":"2024-02-29T16:15:12Z","file_size":289493,"file_name":"Daga_2023_Rautenberg_Paper.pdf","access_level":"open_access","file_id":"52221"}],"publication":"Fortschritte der Akustik - DAGA 2023","type":"conference"},{"publication":"18. Phonetik und Phonologie im deutschsprachigen Raum (P&P)","type":"conference","status":"public","file":[{"file_size":109294,"file_name":"PP_2022_paper_8911.pdf","access_level":"open_access","file_id":"33697","date_updated":"2022-10-12T07:09:26Z","date_created":"2022-10-12T07:09:26Z","creator":"huesera","relation":"main_file","content_type":"application/pdf"}],"_id":"33696","project":[{"name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","_id":"129","grant_number":"438445824"}],"department":[{"_id":"54"},{"_id":"660"}],"user_id":"72602","ddc":["000"],"language":[{"iso":"eng"}],"file_date_updated":"2022-10-12T07:09:26Z","has_accepted_license":"1","year":"2022","citation":{"chicago":"Wiechmann, Jana, Thomas Glarner, Frederik Rautenberg, Petra Wagner, and Reinhold Haeb-Umbach. “Technically Enabled Explaining of Voice Characteristics.” In <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>, 2022.","ieee":"J. Wiechmann, T. Glarner, F. Rautenberg, P. Wagner, and R. Haeb-Umbach, “Technically enabled explaining of voice characteristics,” Bielefeld, 2022.","ama":"Wiechmann J, Glarner T, Rautenberg F, Wagner P, Haeb-Umbach R. Technically enabled explaining of voice characteristics. In: <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>. ; 2022.","bibtex":"@inproceedings{Wiechmann_Glarner_Rautenberg_Wagner_Haeb-Umbach_2022, title={Technically enabled explaining of voice characteristics}, booktitle={18. Phonetik und Phonologie im deutschsprachigen Raum (P&#38;P)}, author={Wiechmann, Jana and Glarner, Thomas and Rautenberg, Frederik and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022} }","short":"J. Wiechmann, T. Glarner, F. Rautenberg, P. Wagner, R. Haeb-Umbach, in: 18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P), 2022.","mla":"Wiechmann, Jana, et al. “Technically Enabled Explaining of Voice Characteristics.” <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>, 2022.","apa":"Wiechmann, J., Glarner, T., Rautenberg, F., Wagner, P., &#38; Haeb-Umbach, R. (2022). Technically enabled explaining of voice characteristics. <i>18. Phonetik Und Phonologie Im Deutschsprachigen Raum (P&#38;P)</i>."},"oa":"1","date_updated":"2023-11-22T13:45:30Z","author":[{"last_name":"Wiechmann","full_name":"Wiechmann, Jana","first_name":"Jana"},{"last_name":"Glarner","full_name":"Glarner, Thomas","first_name":"Thomas"},{"first_name":"Frederik","last_name":"Rautenberg","full_name":"Rautenberg, Frederik","id":"72602"},{"first_name":"Petra","last_name":"Wagner","full_name":"Wagner, Petra"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_created":"2022-10-12T07:10:03Z","title":"Technically enabled explaining of voice characteristics","conference":{"location":"Bielefeld","end_date":"2022-10-07","start_date":"2022-10-06"}},{"date_created":"2023-05-15T07:59:33Z","title":"A Comparison and Combination of Unsupervised Blind Source Separation  Techniques","year":"2021","external_id":{"arxiv":["2106.05627"]},"ddc":["000"],"language":[{"iso":"eng"}],"publication":"ITG Conference on Speech Communication","abstract":[{"text":"Unsupervised blind source separation methods do not require a training phase\r\nand thus cannot suffer from a train-test mismatch, which is a common concern in\r\nneural network based source separation. The unsupervised techniques can be\r\ncategorized in two classes, those building upon the sparsity of speech in the\r\nShort-Time Fourier transform domain and those exploiting non-Gaussianity or\r\nnon-stationarity of the source signals. In this contribution, spatial mixture\r\nmodels which fall in the first category and independent vector analysis (IVA)\r\nas a representative of the second category are compared w.r.t. their separation\r\nperformance and the performance of a downstream speech recognizer on a\r\nreverberant dataset of reasonable size. Furthermore, we introduce a serial\r\nconcatenation of the two, where the result of the mixture model serves as\r\ninitialization of IVA, which achieves significantly better WER performance than\r\neach algorithm individually and even approaches the performance of a much more\r\ncomplex neural network based technique.","lang":"eng"}],"file":[{"file_name":"2106.05627.pdf","access_level":"open_access","file_id":"44856","file_size":295972,"creator":"frra","date_created":"2023-05-16T08:37:31Z","date_updated":"2023-11-15T15:29:32Z","relation":"main_file","content_type":"application/pdf"}],"oa":"1","date_updated":"2023-11-15T15:29:32Z","author":[{"first_name":"Christoph","full_name":"Boeddeker, Christoph","id":"40767","last_name":"Boeddeker"},{"first_name":"Frederik","id":"72602","full_name":"Rautenberg, Frederik","last_name":"Rautenberg"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"main_file_link":[{"open_access":"1","url":"https://arxiv.org/pdf/2106.05627.pdf"}],"conference":{"name":"ITG Conference on Speech Communication","location":"Kiel"},"has_accepted_license":"1","citation":{"ieee":"C. Boeddeker, F. Rautenberg, and R. Haeb-Umbach, “A Comparison and Combination of Unsupervised Blind Source Separation  Techniques,” presented at the ITG Conference on Speech Communication, Kiel, 2021.","chicago":"Boeddeker, Christoph, Frederik Rautenberg, and Reinhold Haeb-Umbach. “A Comparison and Combination of Unsupervised Blind Source Separation  Techniques.” In <i>ITG Conference on Speech Communication</i>, 2021.","ama":"Boeddeker C, Rautenberg F, Haeb-Umbach R. A Comparison and Combination of Unsupervised Blind Source Separation  Techniques. In: <i>ITG Conference on Speech Communication</i>. ; 2021.","apa":"Boeddeker, C., Rautenberg, F., &#38; Haeb-Umbach, R. (2021). A Comparison and Combination of Unsupervised Blind Source Separation  Techniques. <i>ITG Conference on Speech Communication</i>. ITG Conference on Speech Communication, Kiel.","bibtex":"@inproceedings{Boeddeker_Rautenberg_Haeb-Umbach_2021, title={A Comparison and Combination of Unsupervised Blind Source Separation  Techniques}, booktitle={ITG Conference on Speech Communication}, author={Boeddeker, Christoph and Rautenberg, Frederik and Haeb-Umbach, Reinhold}, year={2021} }","short":"C. Boeddeker, F. Rautenberg, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2021.","mla":"Boeddeker, Christoph, et al. “A Comparison and Combination of Unsupervised Blind Source Separation  Techniques.” <i>ITG Conference on Speech Communication</i>, 2021."},"_id":"44843","user_id":"40767","department":[{"_id":"54"}],"file_date_updated":"2023-11-15T15:29:32Z","type":"conference","status":"public"}]