Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 54
  • Download : 0
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel endto-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.
Publisher
JMLR-JOURNAL MACHINE LEARNING RESEARCH
Issue Date
2021-07
Language
English
Citation

International Conference on Machine Learning (ICML)

ISSN
2640-3498
URI
http://hdl.handle.net/10203/288486
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0