Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

             Dongchan Min 1 Dong Bok Lee 1 Eunho Yang 1 2 Sung Ju Hwang 1 2

             Abstract                 synthesis. The majority of the TTS models aim to synthe-
                                  size high quality speech of a single speaker from the given
    With rapid progress in neural text-to-speech (TTS)      text (Oord et al., 2016; Wang et al., 2017; Shen et al., 2018;
    models, personalized speech generation ...