Showing cs.SDShow all
3 papers · 1 filter
cs.SD2024
RAVE for Speech: Efficient Voice Conversion at High Sampling Rates
Anders R. Bargum, Simon Lajboschitz, Cumhur Erkut
Voice conversion has gained increasing popularity within the field of audio manipulation and speech synthesis. Often, the main objective is to transfer the input identity to that o…
cs.SD2023
Reimagining Speech: A Scoping Review of Deep Learning-Powered Voice Conversion
Anders R. Bargum, Stefania Serafin, Cumhur Erkut
Research on deep learning-powered voice conversion (VC) in speech-to-speech scenarios is getting increasingly popular. Although many of the works in the field of voice conversion s…
cs.SD2023
Differentiable Allpass Filters for Phase Response Estimation and Automatic Signal Alignment
Anders R. Bargum, Stefania Serafin, Cumhur Erkut +1
Virtual analog (VA) audio effects are increasingly based on neural networks and deep learning frameworks. Due to the underlying black-box methodology, a successful model will learn…