Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
This work addresses a specific bottleneck in text-to-speech synthesis for applications requiring expressive and natural-sounding speech, representing an incremental improvement.
The paper tackles the degradation of naturalness in expressive speech synthesis when fine-grained latent variables are sampled from a standard Gaussian prior, proposing a hierarchical generative model that improves sampling without reference signals and enables utterance-level style control.
This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine control of the prosody and speaking styles of synthesized speech. However, the naturalness of speech degrades when these latent variables are obtained by sampling from the standard Gaussian prior. To solve this problem, we propose a novel framework for modeling the fine-grained latent variables, considering the dependence on an input text, a hierarchical linguistic structure, and a temporal structure of latent variables. This framework consists of a multi-grained variational autoencoder, a conditional prior, and a multi-level auto-regressive latent converter to obtain the different time-resolution latent variables and sample the finer-level latent variables from the coarser-level ones by taking into account the input text. Experimental results indicate an appropriate method of sampling fine-grained latent variables without the reference signal at the synthesis stage. Our proposed framework also provides the controllability of speaking style in an entire utterance.