Combining audio control and style transfer using latent diffusion

N Demerlé, P Esling, G Doras, D Genova - arXiv preprint arXiv …, 2024 - arxiv.org
Deep generative models are now able to synthesize high-quality audio signals, shifting the
critical aspect in their development from audio quality to control capabilities. Although text-to …

[PDF][PDF] A Computational Approach to Analysis and Detection of Singing Techniques

Y Yamamoto - 2024 - tsukuba.repo.nii.ac.jp
Singing voice is one of the most essential elements of music. It provides impactful emotional
expressions through melody and lyrics and has the potential to move people's hearts and …