Generative adversarial networks in sound synthesis: analysis of sound modeling capabilities using GANs.
This paper explores the capabilities of Generative Adversarial Networks (GANs) for audio synthesis. Particularly, it focus on WaveGAN, which works directly with raw waveforms, and DCGAN trained on spectrogram representations. These models were trained using internal combustion engine sounds collect...
Uloženo v:
| Hlavní autoři: | , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
Lublin University of Technology
2026-06-01
|
| Edice: | Journal of Computer Sciences Institute |
| Témata: | |
| On-line přístup: | https://ph.pollub.pl/index.php/jcsi/article/view/8650 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|