Axial Residual Networks for CycleGAN-based Voice Conversion

We propose a novel architecture and improved training objectives for non-parallel voice conversion. Our proposed CycleGAN-based model performs a shape-preserving transformation directly on a high frequency-resolution magnitude spectrogram, converting its style (i.e. speaker identity) while preservin...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	You, Jaeseong, Nam, Gyuhyeon, Kim, Dalhyun, Chae, Gyeongsu
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Computer Science - Sound
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!