SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-To-Speech Model

• DOI: 10.21437/interspeech.2021-1774
• Publication Date: 2021-08-27T05:59:39Z
• Authors: Edresson Casanova; Christopher Shulby; Eren Gölge; Nicolas Michael M...; Frederico Santos ...; Arnaldo Candido Jr.; Anderson da Silva...; Sandra Maria Aluisio; Moacir Antonelli ...
• Keywords: FOS: Computer and information sciences; Sound (cs.SD); Audio and Speech Processing (eess.AS); FOS: Electrical engineering, electronic engineering, information engineering; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computer Science - Sound; Electrical Engineering and Systems Science - Audio and Speech Processing

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.<br/>Accepted on Interspeech 2021<br/>