[1]
C. Jiang, Y. Gao, W. W. Ng, J. Zhou, J. Zhong, and H. Zhen, “SeDepTTS: Enhancing the Naturalness via Semantic Dependency and Local Convolution for Text-to-Speech Synthesis”, AAAI, vol. 37, no. 11, pp. 12959-12967, Jun. 2023.