[{"language":[{"iso":"eng"}],"department":[{"_id":"54"},{"_id":"660"}],"user_id":"72602","_id":"59999","project":[{"grant_number":"438445824","_id":"129","name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)"}],"status":"public","publication":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","type":"conference","conference":{"start_date":"2025-04-06","name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India ","end_date":"2025-04-11"},"doi":"10.1109/icassp49660.2025.10888012","title":"Speech Synthesis along Perceptual Voice Quality Dimensions","date_created":"2025-05-20T08:17:22Z","author":[{"first_name":"Frederik","last_name":"Rautenberg","full_name":"Rautenberg, Frederik","id":"72602"},{"full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann","first_name":"Michael"},{"full_name":"Seebauer, Fritz","last_name":"Seebauer","first_name":"Fritz"},{"last_name":"Wiechmann","full_name":"Wiechmann, Jana","first_name":"Jana"},{"full_name":"Wagner, Petra","last_name":"Wagner","first_name":"Petra"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_updated":"2025-05-26T11:09:56Z","publisher":"IEEE","citation":{"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>","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>.","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.","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} }","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>","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>.","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>."},"year":"2025","publication_status":"published"},{"citation":{"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>","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>.","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} }","short":"F. Rautenberg, F. Seebauer, J. Wiechmann, M. Kuhlmann, P. Wagner, R. Haeb-Umbach, in: Interspeech 2025, ISCA, 2025.","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>.","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>"},"year":"2025","date_created":"2025-08-28T08:39:01Z","author":[{"last_name":"Rautenberg","id":"72602","full_name":"Rautenberg, Frederik","first_name":"Frederik"},{"last_name":"Seebauer","full_name":"Seebauer, Fritz","first_name":"Fritz"},{"first_name":"Jana","last_name":"Wiechmann","full_name":"Wiechmann, Jana"},{"first_name":"Michael","id":"49871","full_name":"Kuhlmann, Michael","last_name":"Kuhlmann"},{"full_name":"Wagner, Petra","last_name":"Wagner","first_name":"Petra"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_updated":"2025-08-28T08:56:49Z","publisher":"ISCA","conference":{"end_date":"2025-08-21","location":"Rotterdam","name":"Interspeech","start_date":"2025-08-17"},"doi":"10.21437/Interspeech.2025-1443","title":"Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice","type":"conference","publication":"Interspeech 2025","status":"public","user_id":"72602","department":[{"_id":"54"},{"_id":"660"}],"project":[{"_id":"129","name":"TRR 318; TP C06: Technisch unterstütztes Erklären von Stimmcharakteristika"}],"_id":"61047","language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"user_id":"49871","department":[{"_id":"54"}],"_id":"62164","status":"public","type":"conference","publication":"Interspeech 2025","doi":"10.21437/interspeech.2025-2190","title":"Towards Frame-level Quality Predictions of Synthetic Speech","author":[{"first_name":"Michael","id":"49871","full_name":"Kuhlmann, Michael","last_name":"Kuhlmann"},{"last_name":"Seebauer","full_name":"Seebauer, Fritz","first_name":"Fritz"},{"first_name":"Petra","last_name":"Wagner","full_name":"Wagner, Petra","id":"74505"},{"full_name":"Häb-Umbach, Reinhold","id":"242","last_name":"Häb-Umbach","first_name":"Reinhold"}],"date_created":"2025-11-11T11:43:20Z","publisher":"ISCA","date_updated":"2025-11-11T11:45:12Z","citation":{"ama":"Kuhlmann M, Seebauer F, Wagner P, Häb-Umbach R. Towards Frame-level Quality Predictions of Synthetic Speech. In: <i>Interspeech 2025</i>. ISCA; 2025. doi:<a href=\"https://doi.org/10.21437/interspeech.2025-2190\">10.21437/interspeech.2025-2190</a>","chicago":"Kuhlmann, Michael, Fritz Seebauer, Petra Wagner, and Reinhold Häb-Umbach. “Towards Frame-Level Quality Predictions of Synthetic Speech.” In <i>Interspeech 2025</i>. ISCA, 2025. <a href=\"https://doi.org/10.21437/interspeech.2025-2190\">https://doi.org/10.21437/interspeech.2025-2190</a>.","ieee":"M. Kuhlmann, F. Seebauer, P. Wagner, and R. Häb-Umbach, “Towards Frame-level Quality Predictions of Synthetic Speech,” 2025, doi: <a href=\"https://doi.org/10.21437/interspeech.2025-2190\">10.21437/interspeech.2025-2190</a>.","short":"M. Kuhlmann, F. Seebauer, P. Wagner, R. Häb-Umbach, in: Interspeech 2025, ISCA, 2025.","mla":"Kuhlmann, Michael, et al. “Towards Frame-Level Quality Predictions of Synthetic Speech.” <i>Interspeech 2025</i>, ISCA, 2025, doi:<a href=\"https://doi.org/10.21437/interspeech.2025-2190\">10.21437/interspeech.2025-2190</a>.","bibtex":"@inproceedings{Kuhlmann_Seebauer_Wagner_Häb-Umbach_2025, title={Towards Frame-level Quality Predictions of Synthetic Speech}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2025-2190\">10.21437/interspeech.2025-2190</a>}, booktitle={Interspeech 2025}, publisher={ISCA}, author={Kuhlmann, Michael and Seebauer, Fritz and Wagner, Petra and Häb-Umbach, Reinhold}, year={2025} }","apa":"Kuhlmann, M., Seebauer, F., Wagner, P., &#38; Häb-Umbach, R. (2025). Towards Frame-level Quality Predictions of Synthetic Speech. <i>Interspeech 2025</i>. <a href=\"https://doi.org/10.21437/interspeech.2025-2190\">https://doi.org/10.21437/interspeech.2025-2190</a>"},"year":"2025","publication_status":"published"},{"publication":"2024 32nd European Signal Processing Conference (EUSIPCO)","type":"conference","status":"public","_id":"57099","department":[{"_id":"54"}],"user_id":"49871","language":[{"iso":"eng"}],"year":"2024","page":"436–440","citation":{"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} }","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.","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.","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.","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."},"date_updated":"2024-11-15T06:54:40Z","date_created":"2024-11-15T06:52:54Z","author":[{"last_name":"Xie","full_name":"Xie, Yuying","first_name":"Yuying"},{"last_name":"Kuhlmann","full_name":"Kuhlmann, Michael","id":"49871","first_name":"Michael"},{"last_name":"Rautenberg","id":"72602","full_name":"Rautenberg, Frederik","first_name":"Frederik"},{"full_name":"Tan, Zheng-Hua","last_name":"Tan","first_name":"Zheng-Hua"},{"first_name":"Reinhold","last_name":"Häb-Umbach","id":"242","full_name":"Häb-Umbach, Reinhold"}],"title":"Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder"},{"date_created":"2023-10-20T08:04:46Z","title":"On Feature Importance and Interpretability of Speaker Representations","year":"2023","external_id":{"arxiv":["2310.12599"]},"language":[{"iso":"eng"}],"ddc":["000"],"publication":"ITG Conference on Speech Communication","file":[{"content_type":"application/pdf","relation":"main_file","success":1,"date_created":"2023-10-20T08:20:58Z","creator":"frra","date_updated":"2023-10-20T08:20:58Z","access_level":"closed","file_id":"48359","file_name":"arxiv.pdf","file_size":272390}],"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","last_name":"Kuhlmann","id":"49871","full_name":"Kuhlmann, Michael"},{"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"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"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"},"has_accepted_license":"1","citation":{"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.","short":"F. Rautenberg, M. Kuhlmann, J. Wiechmann, F. Seebauer, P. Wagner, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2023.","mla":"Rautenberg, Frederik, et al. “On Feature Importance and Interpretability of Speaker Representations.” <i>ITG Conference on Speech Communication</i>, 2023.","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} }","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."},"user_id":"72602","department":[{"_id":"54"},{"_id":"660"}],"project":[{"name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","_id":"129","grant_number":"438445824"}],"_id":"48355","file_date_updated":"2023-10-20T08:20:58Z","type":"conference","status":"public"},{"author":[{"last_name":"Seebauer","full_name":"Seebauer, Fritz","first_name":"Fritz"},{"last_name":"Kuhlmann","id":"49871","full_name":"Kuhlmann, Michael","first_name":"Michael"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"},{"full_name":"Wagner, Petra","last_name":"Wagner","first_name":"Petra"}],"date_created":"2023-07-15T16:10:20Z","date_updated":"2023-10-25T08:42:56Z","title":"Re-examining the quality dimensions of synthetic speech","has_accepted_license":"1","citation":{"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} }","short":"F. Seebauer, M. Kuhlmann, R. Haeb-Umbach, P. Wagner, in: 12th Speech Synthesis Workshop (SSW) 2023, 2023.","mla":"Seebauer, Fritz, et al. “Re-Examining the Quality Dimensions of Synthetic Speech.” <i>12th Speech Synthesis Workshop (SSW) 2023</i>, 2023.","apa":"Seebauer, F., Kuhlmann, M., Haeb-Umbach, R., &#38; Wagner, P. (2023). Re-examining the quality dimensions of synthetic speech. <i>12th Speech Synthesis Workshop (SSW) 2023</i>.","chicago":"Seebauer, Fritz, Michael Kuhlmann, Reinhold Haeb-Umbach, and Petra Wagner. “Re-Examining the Quality Dimensions of Synthetic Speech.” In <i>12th Speech Synthesis Workshop (SSW) 2023</i>, 2023.","ieee":"F. Seebauer, M. Kuhlmann, R. Haeb-Umbach, and P. Wagner, “Re-examining the quality dimensions of synthetic speech,” 2023.","ama":"Seebauer F, Kuhlmann M, Haeb-Umbach R, Wagner P. Re-examining the quality dimensions of synthetic speech. In: <i>12th Speech Synthesis Workshop (SSW) 2023</i>. ; 2023."},"year":"2023","department":[{"_id":"54"}],"user_id":"242","_id":"46069","project":[{"name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","_id":"129","grant_number":"438445824"}],"language":[{"iso":"eng"}],"publication":"12th Speech Synthesis Workshop (SSW) 2023","type":"conference","status":"public"},{"_id":"44849","project":[{"_id":"129","name":"TRR 318 - C06: TRR 318 - Technisch unterstütztes Erklären von Stimmcharakteristika (Teilprojekt C06)","grant_number":"438445824"}],"department":[{"_id":"54"},{"_id":"660"}],"user_id":"72602","ddc":["000"],"file_date_updated":"2024-02-29T16:15:12Z","language":[{"iso":"eng"}],"publication":"Fortschritte der Akustik - DAGA 2023","type":"conference","status":"public","file":[{"relation":"main_file","content_type":"application/pdf","file_size":289493,"access_level":"open_access","file_id":"52221","file_name":"Daga_2023_Rautenberg_Paper.pdf","date_updated":"2024-02-29T16:15:12Z","creator":"frra","date_created":"2024-02-29T16:15:12Z"}],"oa":"1","date_updated":"2024-02-29T17:05:16Z","author":[{"last_name":"Rautenberg","id":"72602","full_name":"Rautenberg, Frederik","first_name":"Frederik"},{"first_name":"Michael","last_name":"Kuhlmann","full_name":"Kuhlmann, Michael","id":"49871"},{"first_name":"Janek","last_name":"Ebbers","id":"34851","full_name":"Ebbers, Janek"},{"first_name":"Jana","last_name":"Wiechmann","full_name":"Wiechmann, Jana"},{"last_name":"Seebauer","full_name":"Seebauer, Fritz","first_name":"Fritz"},{"last_name":"Wagner","full_name":"Wagner, Petra","first_name":"Petra"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_created":"2023-05-15T08:48:54Z","title":"Speech Disentanglement for Analysis and Modification of Acoustic and Perceptual Speaker Characteristics","conference":{"end_date":"2023-03-09","location":"Hamburg","name":"DAGA 2023 - 49. Jahrestagung für Akustik","start_date":"2023-03-06"},"main_file_link":[{"open_access":"1","url":"https://pub.dega-akustik.de/DAGA_2023/data/articles/000105.pdf"}],"has_accepted_license":"1","publication_status":"published","year":"2023","page":"1409-1412","citation":{"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} }","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."}},{"_id":"57098","user_id":"49871","department":[{"_id":"54"}],"language":[{"iso":"eng"}],"type":"conference","publication":"Proceedings of the 20th International Congress of Phonetic Sciences","status":"public","date_updated":"2024-11-15T06:54:55Z","date_created":"2024-11-15T06:49:27Z","author":[{"first_name":"Fritz","last_name":"Seebauer","full_name":"Seebauer, Fritz"},{"first_name":"Michael","full_name":"Kuhlmann, Michael","id":"49871","last_name":"Kuhlmann"},{"first_name":"Reinhold","last_name":"Häb-Umbach","id":"242","full_name":"Häb-Umbach, Reinhold"},{"first_name":"Petra","full_name":"Wagner, Petra","last_name":"Wagner"}],"title":"DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH","conference":{"start_date":"2023-08-07","name":"International Congress of Phonetic Sciences (ICPhS)","location":"Prague","end_date":"2023-08-11"},"publication_identifier":{"isbn":["978-80-908 114-2-3"]},"year":"2023","citation":{"chicago":"Seebauer, Fritz, Michael Kuhlmann, Reinhold Häb-Umbach, and Petra Wagner. “DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH.” In <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>, 2023.","ieee":"F. Seebauer, M. Kuhlmann, R. Häb-Umbach, and P. Wagner, “DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH,” presented at the International Congress of Phonetic Sciences (ICPhS), Prague, 2023.","ama":"Seebauer F, Kuhlmann M, Häb-Umbach R, Wagner P. DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH. In: <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>. ; 2023.","apa":"Seebauer, F., Kuhlmann, M., Häb-Umbach, R., &#38; Wagner, P. (2023). DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH. <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>. International Congress of Phonetic Sciences (ICPhS), Prague.","short":"F. Seebauer, M. Kuhlmann, R. Häb-Umbach, P. Wagner, in: Proceedings of the 20th International Congress of Phonetic Sciences, 2023.","bibtex":"@inproceedings{Seebauer_Kuhlmann_Häb-Umbach_Wagner_2023, title={DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH}, booktitle={Proceedings of the 20th International Congress of Phonetic Sciences}, author={Seebauer, Fritz and Kuhlmann, Michael and Häb-Umbach, Reinhold and Wagner, Petra}, year={2023} }","mla":"Seebauer, Fritz, et al. “DISCERNING DIMENSIONS OF QUALITY FOR STATE OF THE ART SYNTHETIC SPEECH.” <i>Proceedings of the 20th International Congress of Phonetic Sciences</i>, 2023."}},{"year":"2023","page":"121–125","citation":{"apa":"Kuhlmann, M., Meise, A. T., Seebauer, F., Wagner, P., &#38; Häb-Umbach, R. (2023). Investigating Speaker Embedding Disentanglement on Natural Read Speech. <i>Speech Communication; 15th ITG Conference</i>, 121–125.","short":"M. Kuhlmann, A.T. Meise, F. Seebauer, P. Wagner, R. Häb-Umbach, in: Speech Communication; 15th ITG Conference, 2023, pp. 121–125.","mla":"Kuhlmann, Michael, et al. “Investigating Speaker Embedding Disentanglement on Natural Read Speech.” <i>Speech Communication; 15th ITG Conference</i>, 2023, pp. 121–125.","bibtex":"@inproceedings{Kuhlmann_Meise_Seebauer_Wagner_Häb-Umbach_2023, title={Investigating Speaker Embedding Disentanglement on Natural Read Speech}, booktitle={Speech Communication; 15th ITG Conference}, author={Kuhlmann, Michael and Meise, Adrian Tobias and Seebauer, Fritz and Wagner, Petra and Häb-Umbach, Reinhold}, year={2023}, pages={121–125} }","chicago":"Kuhlmann, Michael, Adrian Tobias Meise, Fritz Seebauer, Petra Wagner, and Reinhold Häb-Umbach. “Investigating Speaker Embedding Disentanglement on Natural Read Speech.” In <i>Speech Communication; 15th ITG Conference</i>, 121–125, 2023.","ieee":"M. Kuhlmann, A. T. Meise, F. Seebauer, P. Wagner, and R. Häb-Umbach, “Investigating Speaker Embedding Disentanglement on Natural Read Speech,” in <i>Speech Communication; 15th ITG Conference</i>, 2023, pp. 121–125.","ama":"Kuhlmann M, Meise AT, Seebauer F, Wagner P, Häb-Umbach R. Investigating Speaker Embedding Disentanglement on Natural Read Speech. In: <i>Speech Communication; 15th ITG Conference</i>. ; 2023:121–125."},"title":"Investigating Speaker Embedding Disentanglement on Natural Read Speech","date_updated":"2026-01-05T10:12:23Z","author":[{"first_name":"Michael","last_name":"Kuhlmann","id":"49871","full_name":"Kuhlmann, Michael"},{"first_name":"Adrian Tobias","last_name":"Meise","full_name":"Meise, Adrian Tobias","id":"79268"},{"full_name":"Seebauer, Fritz","last_name":"Seebauer","first_name":"Fritz"},{"last_name":"Wagner","full_name":"Wagner, Petra","first_name":"Petra"},{"first_name":"Reinhold","last_name":"Häb-Umbach","id":"242","full_name":"Häb-Umbach, Reinhold"}],"date_created":"2024-11-14T09:45:03Z","status":"public","publication":"Speech Communication; 15th ITG Conference","type":"conference","language":[{"iso":"eng"}],"_id":"57086","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"54"}],"user_id":"49871"},{"ddc":["000"],"language":[{"iso":"eng"}],"publication":"Interspeech 2022","file":[{"date_updated":"2023-07-15T16:16:12Z","date_created":"2023-07-15T16:16:12Z","creator":"mikuhl","file_size":303863,"file_id":"46070","access_level":"closed","file_name":"kuhlmann22_interspeech.pdf","content_type":"application/pdf","success":1,"relation":"main_file"}],"publisher":"ISCA","date_created":"2022-10-21T06:50:59Z","title":"Investigation into Target Speaking Rate Adaptation for Voice Conversion","quality_controlled":"1","year":"2022","_id":"33857","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"54"}],"user_id":"34851","file_date_updated":"2023-07-15T16:16:12Z","type":"conference","status":"public","oa":"1","date_updated":"2023-10-25T09:04:45Z","author":[{"first_name":"Michael","last_name":"Kuhlmann","full_name":"Kuhlmann, Michael","id":"49871"},{"full_name":"Seebauer, Fritz","last_name":"Seebauer","first_name":"Fritz"},{"last_name":"Ebbers","full_name":"Ebbers, Janek","id":"34851","first_name":"Janek"},{"last_name":"Wagner","full_name":"Wagner, Petra","first_name":"Petra"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"doi":"10.21437/interspeech.2022-10740","main_file_link":[{"url":"https://www.isca-speech.org/archive/pdfs/interspeech_2022/kuhlmann22_interspeech.pdf","open_access":"1"}],"has_accepted_license":"1","publication_status":"published","citation":{"apa":"Kuhlmann, M., Seebauer, F., Ebbers, J., Wagner, P., &#38; Haeb-Umbach, R. (2022). Investigation into Target Speaking Rate Adaptation for Voice Conversion. <i>Interspeech 2022</i>. <a href=\"https://doi.org/10.21437/interspeech.2022-10740\">https://doi.org/10.21437/interspeech.2022-10740</a>","bibtex":"@inproceedings{Kuhlmann_Seebauer_Ebbers_Wagner_Haeb-Umbach_2022, title={Investigation into Target Speaking Rate Adaptation for Voice Conversion}, DOI={<a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>}, booktitle={Interspeech 2022}, publisher={ISCA}, author={Kuhlmann, Michael and Seebauer, Fritz and Ebbers, Janek and Wagner, Petra and Haeb-Umbach, Reinhold}, year={2022} }","mla":"Kuhlmann, Michael, et al. “Investigation into Target Speaking Rate Adaptation for Voice Conversion.” <i>Interspeech 2022</i>, ISCA, 2022, doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>.","short":"M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, R. Haeb-Umbach, in: Interspeech 2022, ISCA, 2022.","ieee":"M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, and R. Haeb-Umbach, “Investigation into Target Speaking Rate Adaptation for Voice Conversion,” 2022, doi: <a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>.","chicago":"Kuhlmann, Michael, Fritz Seebauer, Janek Ebbers, Petra Wagner, and Reinhold Haeb-Umbach. “Investigation into Target Speaking Rate Adaptation for Voice Conversion.” In <i>Interspeech 2022</i>. ISCA, 2022. <a href=\"https://doi.org/10.21437/interspeech.2022-10740\">https://doi.org/10.21437/interspeech.2022-10740</a>.","ama":"Kuhlmann M, Seebauer F, Ebbers J, Wagner P, Haeb-Umbach R. Investigation into Target Speaking Rate Adaptation for Voice Conversion. In: <i>Interspeech 2022</i>. ISCA; 2022. doi:<a href=\"https://doi.org/10.21437/interspeech.2022-10740\">10.21437/interspeech.2022-10740</a>"}},{"file_date_updated":"2022-01-13T08:19:19Z","user_id":"34851","department":[{"_id":"54"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"29304","status":"public","type":"conference","author":[{"full_name":"Ebbers, Janek","id":"34851","last_name":"Ebbers","first_name":"Janek"},{"first_name":"Michael","last_name":"Kuhlmann","id":"49871","full_name":"Kuhlmann, Michael"},{"first_name":"Tobias","id":"44393","full_name":"Cord-Landwehr, Tobias","last_name":"Cord-Landwehr"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2023-11-22T08:29:42Z","oa":"1","citation":{"chicago":"Ebbers, Janek, Michael Kuhlmann, Tobias Cord-Landwehr, and Reinhold Haeb-Umbach. “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations.” In <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 3860–3864, 2021.","ieee":"J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, and R. Haeb-Umbach, “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations,” in <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2021, pp. 3860–3864.","ama":"Ebbers J, Kuhlmann M, Cord-Landwehr T, Haeb-Umbach R. Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations. In: <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2021:3860–3864.","apa":"Ebbers, J., Kuhlmann, M., Cord-Landwehr, T., &#38; Haeb-Umbach, R. (2021). Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations. <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 3860–3864.","bibtex":"@inproceedings{Ebbers_Kuhlmann_Cord-Landwehr_Haeb-Umbach_2021, title={Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, author={Ebbers, Janek and Kuhlmann, Michael and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}, year={2021}, pages={3860–3864} }","short":"J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, R. Haeb-Umbach, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 3860–3864.","mla":"Ebbers, Janek, et al. “Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations.” <i>Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2021, pp. 3860–3864."},"page":"3860–3864","has_accepted_license":"1","language":[{"iso":"eng"}],"ddc":["000"],"file":[{"file_name":"Template.pdf","file_id":"29305","access_level":"open_access","file_size":236628,"creator":"ebbers","date_created":"2022-01-13T07:56:30Z","date_updated":"2022-01-13T08:19:19Z","relation":"main_file","content_type":"application/pdf"}],"abstract":[{"text":"In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose adversarial contrastive predictive coding. This new disentanglement method does neither need parallel data nor any supervision. We show that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches. We further demonstrate an increased robustness of the content representation against a train-test mismatch compared to spectral features, when used for phone recognition.","lang":"eng"}],"publication":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","title":"Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations","date_created":"2022-01-13T07:55:29Z","year":"2021","quality_controlled":"1"}]