GANtron: Emotional Speech Synthesis with Generative Adversarial Networks
This work addresses the need for more expressive and user-friendly speech synthesis tools, though it appears incremental as it builds on existing GAN and attention-based methods.
The paper tackled the problem of robotic-sounding speech synthesis by developing a text-to-speech model that allows easy tuning of emotions in generated speech, using GANs and a sequence-to-sequence model with attention, and proved that their best model generates speech matching the training data distribution.
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.