Debut albums have been essential topics of discussion since Sun Records put out Elvis Presley back in 1956. Since then, some of the most cornerstone works in music occurred on debuts—be it The Doors, ...
Abstract: This paper introduces V2Coder, a non-autoregressive vocoder based on hierarchical variational autoencoders (VAEs). The hierarchical VAE with hierarchically extended prior and approximate ...
Abstract: We propose a joint training scheme of an any-to-one voice conversion (VC) system with LPCNet to improve the speech naturalness, speaker similarity, and intelligibility of the converted ...
Underlined "TTS*" and "Judy*" are internal 🐸TTS models that are not released open-source. They are here to show the potential. Models prefixed with a dot (.Jofish ...
In this paper, we propose the application of speaker embedding networks for zero-shot SVC. We suggest two architectures for carrying out zero-shot SVC using the WORLD vocoder for modeling singing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback