DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Jaehyeon | ko |
dc.contributor.author | Kong, Jungil | ko |
dc.contributor.author | Son, Juhee | ko |
dc.date.accessioned | 2021-11-01T06:42:00Z | - |
dc.date.available | 2021-11-01T06:42:00Z | - |
dc.date.created | 2021-10-27 | - |
dc.date.issued | 2021-07 | - |
dc.identifier.citation | International Conference on Machine Learning (ICML) | - |
dc.identifier.issn | 2640-3498 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288486 | - |
dc.description.abstract | 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. | - |
dc.language | English | - |
dc.publisher | JMLR-JOURNAL MACHINE LEARNING RESEARCH | - |
dc.title | Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech | - |
dc.type | Conference | - |
dc.identifier.wosid | 000683104605052 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | International Conference on Machine Learning (ICML) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | ELECTR NETWORK | - |
dc.contributor.localauthor | Son, Juhee | - |
dc.contributor.nonIdAuthor | Kim, Jaehyeon | - |
dc.contributor.nonIdAuthor | Kong, Jungil | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.