GANtron: Emotional Speech Synthesis with Generative Adversarial Networks

Autor:	Hortal, Enrique, Alarcia, Rodrigo Brechard
Rok vydání:	2021
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence Electrical Engineering and Systems Science - Audio and Speech Processing 68-T07 62H30 I.2 I.6.2
Druh dokumentu:	Working Paper
Popis:	Speech synthesis is used in a wide variety of industries. Nonetheless, it always sounds flat or robotic. The state of the art methods that allow for prosody control are very cumbersome to use and do not allow easy tuning. To tackle some of these drawbacks, in this work we target the implementation of a text-to-speech model where the inferred speech can be tuned with the desired emotions. To do so, we use Generative Adversarial Networks (GANs) together with a sequence-to-sequence model using an attention mechanism. We evaluate four different configurations considering different inputs and training strategies, study them and prove how our best model can generate speech files that lie in the same distribution as the initial training dataset. Additionally, a new strategy to boost the training convergence by applying a guided attention loss is proposed. Comment: 9 pages, 4 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2110.03390 Zobrazit plný text záznamu View this record from Arxiv