EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance

TL;DR

EmoDiff is a diffusion-based TTS model that enables precise control of emotional intensity in speech through a novel soft-label guidance technique, maintaining high quality and diversity.

Contribution

It introduces a soft-label guidance method for emotion intensity control in diffusion-based TTS, improving flexibility and quality over existing approaches.

Findings

Accurately controls emotion intensity in speech

Maintains high speech quality during control

Generates diverse emotional speech samples

Abstract

Although current neural text-to-speech (TTS) models are able to generate high-quality speech, intensity controllable emotional TTS is still a challenging task. Most existing methods need external optimizations for intensity calculation, leading to suboptimal results or degraded quality. In this paper, we propose EmoDiff, a diffusion-based TTS model where emotion intensity can be manipulated by a proposed soft-label guidance technique derived from classifier guidance. Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where the value of the specified emotion and \textit{Neutral} is set to $\alpha$ and $1-\alpha$ respectively. The $\alpha$ here represents the emotion intensity and can be chosen from 0 to 1. Our experiments show that EmoDiff can precisely control the emotion intensity while maintaining high voice quality. Moreover, diverse speech with specified emotion intensity can be generated by sampling in the reverse denoising process.