PUMA

Akademisches Publikationsmanagement
Publikationen sammeln, verwalten und teilen.

( en | de )

 

Disambiguierung von "Tilli, Pascal"

Autor der Publikation

KopierenLöschenDiese Publikation zur Ablage hinzufügen
Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy

, , , , , und . 2022 IEEE Spoken Language Technology Workshop (SLT), Seite 912--919. IEEE, (2023)

Bitte wählen Sie eine Person um die Publikation zuzuordnen

Um zwischen Personen mit demselben Namen zu unterscheiden, wird der akademische Grad und der Titel einer wichtigen Publikation angezeigt. Zudem lassen sich über den Button neben dem Namen einige der Person bereits zugeordnete Publikationen anzeigen.

Pascal Tilli University of Stuttgart

Pascal Gröger University of Stuttgart

Pascal Heinzelmann University of Stuttgart

Pascal Strobel University of Stuttgart

Pascal Goldschmid University of Stuttgart

 

Weitere Publikationen von Autoren mit dem selben Namen

Beyond Accuracy : A Consolidated Tool for Visual Question Answering Benchmarking, , und . Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing : System Demonstrations, Seite 114-123. Stroudsburg, Association for Computational Linguistics, (2021)Explaining Caption-Image Interactions in CLIP models with Second-Order Attributions, , , und . (2024)Manuscript.Extended Visual Analysis System for Scene-Graph-Based Visual Question Answering, , , , , , und . Software, (2025)Related to: Künzel, S., Munz-Körner, T., Tilli, P. et al. Visual explainable artificial intelligence for graph-based visual question answering and scene graph curation. Vis. Comput. Ind. Biomed. Art 8, 9 (2025). doi: 10.1186/s42492-025-00185-y.Intrinsic Subgraph Generation for Interpretable Graph Based Visual Question Answering, und . Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Seite 9204-9223. ELRA And ICCL, (2024)Prosody Is Not Identity : A Speaker Anonymization Approach Using Prosody Cloning, , , , , und . ICASSP 2023 : 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, (2023)Data for: HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities. Dataset, (2024)Related to: Esra Dönmez*, Pascal Tilli*, Hsiu-Yu Yang*, Ngoc Thang Vu, and Carina Silberer. 2023. HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities. In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pages 364-388, Singapore. Association for Computational Linguistics. doi: 10.18653/v1/2023.conll-1.24.HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities, , , , und . Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), Seite 364--388. Singapore, Association for Computational Linguistics, (Dezember 2023)Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions, , , und . 24th Annual Conference of the International Speech Communication Association (INTERSPEECH 2023), 8, Seite 4788-4792. Red Hook, NY, Curran Associates, Inc., (2023)Explaining Vision-Language Similarities in Dual Encoders with Feature-Pair Attributions, , , und . Preprint, (2024)Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy, , , , , und . 2022 IEEE Spoken Language Technology Workshop (SLT), Seite 912-919. IEEE, (2022)