EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance
This work addresses a specific problem in neural TTS for applications requiring nuanced emotional expression, representing an incremental improvement over existing methods.
The paper tackles the challenge of intensity controllable emotional text-to-speech (TTS) by proposing EmoDiff, a diffusion-based model that uses a soft-label guidance technique to manipulate emotion intensity, achieving precise control while maintaining high voice quality.
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 $α$ and $1-α$ respectively. The $α$ 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.