Speech Synthesis of Emotions in a Sentence using Vowel Features
Rintaro Makino, Yasunari Yoshitomi, Taro Asada, Masayoshi Tabuse · Journal of Robotics Networking and Artificial Life · 2020
We previously proposed a method for adding emotions to synthetic speech using the vowel features of a speaker. For the initial investigation in this earlier study, we used utterances of Japanese names to demonstrate the method. In the present study, we use the proposed method to construct emotional synthetic speech for a sentence formed from the emotional speech of a single male subject and produce results that are discriminable with good accuracy.