Implicit vs. Explicit Style Transfer? A Comparison of GAN Architectures for Continuous Path Keyboard Input Modeling

The success of continuous path keyboard input as an alternative text input modality requires high-quality training data to inform the underlying recognition model. In [1], we have adopted generative adversarial networks (GANs) to augment the training corpus with synthetic user-realistic paths. GAN-driven synthesis makes it possible to emulate the acquisition of enough paths from enough users to learn a model sufficiently robust across a large population. The present work studies the influence of different GAN architectures on path quality and diversity. Experiments show that explicit content/ style disentanglement resulting from separate style encoding has only a limited impact on end user perception. On the other hand, implicit and explicit style transfer paradigms are complementary in the kind of user-realistic artifacts they generate. Leveraging multiple GAN strategies thus injects more robustness into the model through broader coverage of user idiosyncrasies across a wide lexical range.