When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds

Minsu Kang, Seolhee Lee, Choonghyeon Lee +1

Human to non-human voice conversion (H2NH-VC) transforms human speech into animal or designed vocalizations. Unlike prior studies focused on dog-sounds and 16 or 22.05kHz audio tra…