Alternative Vietnamese Speech Synthesis System with Phoneme Structure
Quang Tuong Lam, Hao D., Hung Vo, Duc Dung Nguyen · 2019
This paper proposes an alternative approach for synthesizing Vietnamese speech. In order to improve the naturalness and intelligibility of the speech synthesizer, we propose the Vietnamese phoneme model and integrate into an end-to-end model. We employ the pipeline of Tacotron 2 model with attention scheme to generate high-quality speeches. As we replace the character embedding model with Vietnamese phoneme model, we obtain promising results. In addition, we also create a tool for converting Vietnamese text to phoneme sequence. The new phoneme embedding method can also be applied to various languages, while we can take the advantages of state-of-the-art models.