Web: http://arxiv.org/abs/2206.08790

June 20, 2022, 1:12 a.m. | Marc-Antoine Georges, Jean-Luc Schwartz, Thomas Hueber

cs.CL updates on arXiv.org arxiv.org

The human perception system is often assumed to recruit motor knowledge when
processing auditory speech inputs. Using articulatory modeling and deep
learning, this study examines how this articulatory information can be used for
discovering speech units in a self-supervised setting. We used vector-quantized
variational autoencoders (VQ-VAE) to learn discrete representations from
articulatory and acoustic speech data. In line with the zero-resource paradigm,
an ABX test was then used to investigate how the extracted representations
encode phonetically relevant properties. Experiments were …

arxiv discovery features speech

More from arxiv.org / cs.CL 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