$\rm{Yoori\ Oh^{1}, Juheon\ Lee^{2}, Yoseob\ Han^{5}, Kyogu\ Lee^{1,3,4} }$

$\rm{Department\ of\ Intelligence\ and\ Information,\ Seoul\ National\ University^{1}}$

$\rm{Institute\ of\ New\ Media\ and\ Communications,\ Seoul\ National\ University^{2}}$

$\rm{Interdisciplinary\ Program\ in\ Artificial\ Intelligence,\ Seoul\ National\ University^{3}}$

$\rm{Artificial\ Intelligence\ Institute,\ Seoul\ National\ University^{4}}$

$\rm{School\ of\ Electronic\ Engineering,\ Soongsil\ University^{5}}$

Abstract

Recent text-to-speech models have reached the level of generating natural speech similar to what humans say. But there still have limitations in terms of expressiveness. The existing emotional speech synthesis models have shown controllability using interpolated features with scaling parameters in emotional latent space. However, the emotional latent space generated from the existing models is difficult to control the continuous emotional intensity because of the entanglement of features like emotions, speakers, etc. In this paper, we propose a novel method to control the continuous intensity of emotions using semi-supervised learning. The model learns emotions of intermediate intensity using pseudo-labels generated from phoneme-level sequences of speech information. An embedding space built from the proposed model satisfies the uniform grid geometry with an emotional basis. The experimental results showed that the proposed method was superior in controllability and naturalness.