“ClariNet: Parallel Wave Generation in End-To-End Text-To-Speech”, 2018-07-19 (; backlinks; similar):
In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den et al 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a regularized KL divergence between their highly-peaked output distributions.
Our method computes the KL divergence in closed-form, which simplifies the training algorithm and provides very efficient distillation. In addition, we introduce the first text-to-wave neural architecture for speech synthesis, which is fully convolutional and enables fast end-to-end training from scratch.
It outperforms the previous pipeline that connects a text-to-spectrogram model to a separately trained WaveNet ( et al 2018). We also successfully distill a parallel waveform synthesizer conditioned on the hidden representation in this end-to-end model.