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...
Gorde:
| Egile Nagusiak: | , |
|---|---|
| Formatua: | Artigo |
| Hizkuntza: | Inglês |
| Argitaratua: |
Lublin University of Technology
2026-06-01
|
| Saila: | Journal of Computer Sciences Institute |
| Gaiak: | |
| Sarrera elektronikoa: | https://ph.pollub.pl/index.php/jcsi/article/view/8650 |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|