Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Hedelin, Per"'
We consider audio decoding as an inverse problem and solve it through diffusion posterior sampling. Explicit conditioning functions are developed for input signal measurements provided by an example of a transform domain perceptual audio codec. Viabi
Externí odkaz:
http://arxiv.org/abs/2409.07858
Publikováno v:
2023 31st European Signal Processing Conference (EUSIPCO)
We provide an example of a distribution preserving source separation method, which aims at addressing perceptual shortcomings of state-of-the-art methods. Our approach uses unconditioned generative models of signal sources. Reconstruction is achieved
Externí odkaz:
http://arxiv.org/abs/2303.05896
We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality of state-of-the-art classic wide-band codecs. Moreover, it is demonst
Externí odkaz:
http://arxiv.org/abs/1811.03021
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Shabestary, Turaj Zakizadeh1 turaj.za-kizadehshabestary@maiLmcgill.ca, Hedelin, Per2 per.hedelin@elmagn.chalrners.se
Publikováno v:
IEEE Transactions on Information Theory. Feb2005, Vol. 51 Issue 2, p738-746. 9p.
Autor:
Skoglund, Mikael, Hedelin, Per
Publikováno v:
IEEE Transactions on Information Theory. Mar99, Vol. 45 Issue 2, p515. 18p. 3 Diagrams, 5 Charts, 5 Graphs.
Autor:
Hagen, Roar, Hedelin, Per
Publikováno v:
IEEE Transactions on Information Theory. Jan99, Vol. 45 Issue 1, p200. 19p. 5 Diagrams, 5 Charts, 4 Graphs.
Autor:
Norden, Fredrik, Hedelin, Per
Publikováno v:
2002 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2002, pI653-I656, 4p
Publikováno v:
2002 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2002, pI641-I644, 4p
Autor:
Lindblom, Jonas, Hedelin, Per
Publikováno v:
2002 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2002, pI173-I176, 4p