notesum.ai

Published at November 22

VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space

eess.AS

Released Date: November 22, 2024

Authors: Armani Rodriguez1, Silvija Kokalj-Filipovic1

Aff.: 1Rowan University

Arxiv: http://arxiv.org/abs/2411.14642v1