SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model
Abstract
In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training. We propose a speaker-conditional architecture that explores a flow-based decoder that works in a zero-shot scenario. As text encoders, we explore a dilated residual convolutional-based encoder, gated convolutional-based encoder, and transformer-based encoder. Additionally, we have shown that adjusting a GAN-based vocoder for the spectrograms predicted by the TTS model on the training dataset can significantly improve the similarity and speech quality for new speakers. Our model converges using only 11 speakers, reaching state-of-the-art results for similarity with new speakers, as well as high speech quality.
Cite
@article{arxiv.2104.05557,
title = {SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model},
author = {Edresson Casanova and Christopher Shulby and Eren Gölge and Nicolas Michael Müller and Frederico Santos de Oliveira and Arnaldo Candido Junior and Anderson da Silva Soares and Sandra Maria Aluisio and Moacir Antonelli Ponti},
journal= {arXiv preprint arXiv:2104.05557},
year = {2021}
}
Comments
Accepted on Interspeech 2021