Web: http://arxiv.org/abs/2206.02246

June 23, 2022, 1:11 a.m. | Alon Levkovitch, Eliya Nachmani, Lior Wolf

cs.LG updates on arXiv.org arxiv.org

We present a novel way of conditioning a pretrained denoising diffusion
speech model to produce speech in the voice of a novel person unseen during
training. The method requires a short (~3 seconds) sample from the target
person, and generation is steered at inference time, without any training
steps. At the heart of the method lies a sampling process that combines the
estimation of the denoising model with a low-pass version of the new speaker's
sample. The objective and subjective …

arxiv denoising models tts voice

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY