Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
This work addresses speech synthesis for applications requiring high-quality synthetic speech, representing an incremental improvement by integrating recurrent units into an existing DGP framework.
The paper tackled the problem of improving naturalness in speech synthesis by applying deep Gaussian processes (DGP) with a recurrent architecture at the utterance level, using a simple recurrent unit (SRU). The results showed that the proposed SRU-DGP model outperformed feed-forward DGP and tuned neural networks in objective and subjective evaluations.
This paper presents a deep Gaussian process (DGP) model with a recurrent architecture for speech sequence modeling. DGP is a Bayesian deep model that can be trained effectively with the consideration of model complexity and is a kernel regression model that can have high expressibility. In the previous studies, it was shown that the DGP-based speech synthesis outperformed neural network-based one, in which both models used a feed-forward architecture. To improve the naturalness of synthetic speech, in this paper, we show that DGP can be applied to utterance-level modeling using recurrent architecture models. We adopt a simple recurrent unit (SRU) for the proposed model to achieve a recurrent architecture, in which we can execute fast speech parameter generation by using the high parallelization nature of SRU. The objective and subjective evaluation results show that the proposed SRU-DGP-based speech synthesis outperforms not only feed-forward DGP but also automatically tuned SRU- and long short-term memory (LSTM)-based neural networks.