Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail projektu
Období řešení: 01.01.2023 — 31.12.2025
Zdroje financování
Grantová agentura České republiky - Standardní projekty
- plně financující
O projektu
Popis anglickyState-of-the-art methods for the reconstruction of degraded audio signals are successful at their performance. However, they still suffer from perceptually unpleasant or annoying artifacts coming from the reconstruction process. Only a few recent approaches involved psychoacoustics to alleviate this disturbing phenomena. Unfortunately, it turns out that the incorporation of auditory models into current methods it strongly limited. Their use therein is prevented by their complexity, non-differentiability and non-convexity. Recent results from the field of deep learning show that functionals can be trained to distinguish between faithful and implausible audio. Such discriminators come in the form of a neural network, thus being non-linear and non-convex, but, most importantly, differentiable. The project aims at using these discriminators as universal regularizers in algorithms inspired in convex optimization. This will not only lead to a general reconstruction framework, but also to significant improvements of perceptual quality in a wide range of audio inverse problems.
Klíčová slovarekonstrukce signálu; regularizace; hluboké učení; neuronová síť; iterativní algoritmy; diskriminátor; kodek
Klíčová slova anglickysignal processing, audio, signal reconstruction, regularization, deep learning, neural network, discriminator, iterative algorithms, auditory modeling, psychoacoustics
Označení
23-07294S
Originální jazyk
čeština
Řešitelé
Rajmic Pavel, prof. Mgr., Ph.D. - hlavní řešitel
Útvary
Ústav telekomunikací- příjemce (31.03.2022 - nezadáno)
Výsledky
ŠVENTO, M.; BALUŠÍK, P. Deep prior audio compression. Proceedings I of the 30th Student EEICT 2024 (General Papers). Proceedings II of the Conference STUDENT EEICT. 1. Brno: Brno University of Technology, Faculty of Electrical Engineering and Communication, 2024. ISSN: 2788-1334.Detail
ZÁVIŠKA, P.; RAJMIC, P.; MOKRÝ, O. Multiple Hankel matrix rank minimization for audio inpainting. In Proceedings of the 2023 46th International Conference on Telecommunications and Signal Processing (TSP). Prague, Czech republic: IEEE, 2023. p. 47-51. ISBN: 979-8-3503-0396-4.Detail