EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech

TL;DR

EmoSphere-TTS introduces a novel spherical emotion vector approach for controllable, nuanced emotional speech synthesis, enabling manipulation of emotional style and intensity without human annotations.

Contribution

The paper presents a new spherical emotion vector and dual adversarial network for high-quality, controllable emotional TTS without requiring human-labeled data.

Findings

Effective control of emotional style and intensity in speech synthesis.

High-quality expressive speech generated with the proposed method.

Model captures complex emotional nuances without human annotations.

Abstract

Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion. As a result, the ability to manipulate speech emotion remains constrained to several predefined labels, compromising the ability to reflect the nuanced variations of emotion. In this paper, we propose EmoSphere-TTS, which synthesizes expressive emotional speech by using a spherical emotion vector to control the emotional style and intensity of the synthetic speech. Without any human annotation, we use the arousal, valence, and dominance pseudo-labels to model the complex nature of emotion via a Cartesian-spherical transformation. Furthermore, we propose a dual conditional adversarial network to improve the quality of generated speech by reflecting the multi-aspect characteristics. The experimental results demonstrate the model ability to control emotional style and intensity with high-quality expressive speech.