Journal paper on audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders

Journal paper in Computer Speech & Language:

Enhanced Audio-Visual Speech Enhancement with Posterior Sampling Methods in Recurrent Variational Autoencoders.

Zohre Foroushi and Prof. Richard Dansereau published an open access journal article in Computer Speech & Language on using posterior sampling methods in recurrent variational auto encoders to improve audio-visual speech enhancement.