Knowledge distillation (KD) is an efficient framework for compressing
la...
Intermediate layer knowledge distillation (KD) can improve the standard ...
End-to-end automatic speech recognition (ASR), unlike conventional ASR, ...
Adversarial training of end-to-end (E2E) ASR systems using generative
ad...
While significant improvements have been made in recent years in terms o...
Word-embeddings are a vital component of Natural Language Processing (NL...
Text generation is of particular interest in many NLP applications such ...
Text generation with generative adversarial networks (GANs) can be divid...
Latent space based GAN methods and attention based sequence to sequence
...
Inspired by the success of self attention mechanism and Transformer
arch...