Projekter pr. år
Organisationsprofil
Organisationsprofil
The Machine Learning group conducts research in advancing machine learning methods and developing applications for a variety of signals and data, aiming to provide advanced AI solutions to real-world problems. The group focuses its research on learning theory and algorithms, deep learning, representation learning, learning from speech and multimodal data, and applications of machine learning.
Fingerprint
Fingerprint er automatisk genererede koncepter, som relaterer til enhedens profil, samt indholdet i de tilknyttede personprofiler. Det opdateres løbende med tilføjelsen af nye registreringer.
Samarbejde i de sidste fem år
Klik på punkterne for at se detaljerne.
Profiler
-
Classique - Center for Classical Communication in the Quantum Era
Popovski, P. (PI (principal investigator)), Østergaard, J. (CoI (co-investigator)), Pedersen, T. G. (CoI (co-investigator)), Cornean, H. (CoI (co-investigator)) & Larsen, K. G. (CoI (co-investigator))
01/02/2025 → 31/01/2031
Projekter: Projekt › Forskning
-
Speech Enhancement using Sequence Modelling Neural Architectures and Spoken Large Language Models
Kühne, N. (PI (principal investigator)), Tan, Z.-H. (Supervisor), Østergaard, J. (Supervisor) & Jensen, J. (Supervisor)
02/09/2024 → 31/08/2028
Projekter: Projekt › Ph.d.-projekt
-
AAU Water
Lykke, A. (Projektkoordinator), Quist-Jensen, C. A. (PI (principal investigator)), Vollertsen, J. (PI (principal investigator)), Nielsen, P. H. (PI (principal investigator)), Larsen, K. G. (PI (principal investigator)), Ali, A. (PI (principal investigator)), Aschmoneit, F. J. (PI (principal investigator)), Pomianowski, M. Z. (PI (principal investigator)) & Wisniewski, R. (PI (principal investigator))
01/05/2024 → …
Projekter: Projekt › Forskning
Publikationer
-
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models
Kühne, N. L., Kitchen, A. H. F., Saugstrup Jensen, M., Brøndt, M. S. L., Gonzalez, M., Biscio, C. & Tan, Z.-H., apr. 2025, 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (Institute of Electrical and Electronics Engineers), 5 s.Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review
Åben adgangFil28 Downloads (Pure) -
Effects of Reduced Information in the Performance of Low-Frequency Sound Zones
Cadavid, J., Møller, M. B., van Waterschoot, T., Bech, S. & Østergaard, J., 2025, (Accepteret/In press) I: Journal of the Audio Engineering Society.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review
Åben adgangFil2 Downloads (Pure) -
Handling Domain Shifts for Anomalous Sound Detection: A Review of DCASE-Related Work
Wilkinghoff, K., Fujimura, T., Imoto, K., Le Roux, J., Tan, Z.-H. & Toda, T., 13 mar. 2025, arXiv, 5 s.Publikation: Working paper/Preprint › Preprint
Åben adgangFil4 Downloads (Pure)
Forskningsdatasæt
-
Room Impulse Responses for Low-Frequency Sound Field Control
Cadavid Tobón, J. M. (Ophavsperson), Møller, M. B. (Bidrager), van Waterschoot, T. (Bidrager), Bech, S. (Bidrager) & Østergaard, J. (Bidrager), Zenodo, 15 jun. 2024
Datasæt
-
Can real-ear insertion gain deviations from generic fitting prescriptions predict self-reported outcomes?
Narayanan, S. K. (Ophavsperson), Rye, P. (Ophavsperson), Piechowiak, T. (Ophavsperson), Ravn, G. (Ophavsperson), Wolff, A. (Ophavsperson), Houmøller, S. S. (Ophavsperson), Schmidt, J. H. (Ophavsperson) & Hammershøi, D. (Ophavsperson), Taylor & Francis, 7 apr. 2022
DOI: 10.6084/m9.figshare.19538156.v1, https://tandf.figshare.com/articles/journal_contribution/Can_real-ear_insertion_gain_deviations_from_generic_fitting_prescriptions_predict_self-reported_outcomes_/19538156/1
Datasæt: Supplerende materiale
Priser
-
Best Student Paper
Cadavid Tobón, J. M. (Modtager), Møller, M. B. (Modtager), van Waterschoot, T. (Modtager), Bech, S. (Modtager) & Østergaard, J. (Modtager), 15 jun. 2024
Pris: Konferencepriser
Aktiviteter
-
Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations
Yadav, S. (Foredragsholder)
2 sep. 2024Aktivitet: Foredrag og mundtlige bidrag › Konferenceoplæg
-
Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
Yadav, S. (Foredragsholder)
9 maj 2024Aktivitet: Foredrag og mundtlige bidrag › Konferenceoplæg
-
Felix Agner
Wisniewski, R. (Vært)
27 nov. 2023 → 1 dec. 2023Aktivitet: Værtskab for gæsteforsker › Værtskab for gæsteforsker
Presse/medier
-
Kunstig intelligens skal maksimere havvindmøllers produktion
29/04/2024
2 elementer af Mediedækning
Presse/medie
-
-
Samarbejder på tværs skal klæde os på til fremtidens smarte vandsystemer
Jessen, J. F., Andersen, A. O., Wisniewski, R., Rathore, S. S. & Kallesøe, C.
25/04/2023
2 Mediebidrag
Presse/medie