StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis
This addresses the problem of generating more expressive and natural speech for audiobooks, which is an incremental improvement over existing methods.
The paper tackled the limited expressive quality in audiobook speech synthesis by proposing a self-supervised style enhancing method with VQ-VAE-based pre-training, resulting in improved naturalness and expressiveness, especially for role and out-of-domain scenarios as shown in objective and subjective evaluations.
The expressive quality of synthesized speech for audiobooks is limited by generalized model architecture and unbalanced style distribution in the training data. To address these issues, in this paper, we propose a self-supervised style enhancing method with VQ-VAE-based pre-training for expressive audiobook speech synthesis. Firstly, a text style encoder is pre-trained with a large amount of unlabeled text-only data. Secondly, a spectrogram style extractor based on VQ-VAE is pre-trained in a self-supervised manner, with plenty of audio data that covers complex style variations. Then a novel architecture with two encoder-decoder paths is specially designed to model the pronunciation and high-level style expressiveness respectively, with the guidance of the style extractor. Both objective and subjective evaluations demonstrate that our proposed method can effectively improve the naturalness and expressiveness of the synthesized speech in audiobook synthesis especially for the role and out-of-domain scenarios.