SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model
This improves speech synthesis for applications requiring diverse voices, though it is incremental as it builds on existing flow-based and GAN methods.
The paper tackles the problem of generating speech for unseen speakers in zero-shot multi-speaker text-to-speech, achieving state-of-the-art similarity results with high speech quality using only 11 speakers for training.
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.