Reconstruction of Audio Recordings Using Machine Learning Techniques (CROSBI ID 431792)
Ocjenski rad | diplomski rad
Podaci o odgovornosti
Kordiš, Lovro
Delač, Goran
engleski
Reconstruction of Audio Recordings Using Machine Learning Techniques
Audio super resolution is still a developing field in deep learning. This paper deals with generative adversarial networks and using the adversarial training on pairs of low and high resolution audios to create a model for audio super resolution. Deep convolutional and generative adversarial networks are described in detail. A deep convolutional U-Net adversarial model is implemented, and two adversarial loss functions are tested - Wasserstein and Relativistic loss. Model is evaluated on VCTK dataset. Finally, the results and spectogram images are presented.
machine learning ; deep learning ; generative adversarial networks ; audio super resolution
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o izdanju
44
09.07.2019.
obranjeno
Podaci o ustanovi koja je dodijelila akademski stupanj
Fakultet elektrotehnike i računarstva
Zagreb