Speech Synthesis and Control Using Differentiable DSP
This work addresses the need for more controllable speech synthesis systems, offering incremental improvements by adapting DDSP from music to speech for enhanced variation control.
The paper tackled the problem of generating diverse speech renditions from text by enabling explicit control over factors like pitch and timbre, proposing a neural vocoder using differentiable digital signal processing (DDSP) that produces natural speech with realistic timbre and allows free control of individual variation factors.
Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\ that text alone cannot contain. In this work we move towards a speech synthesis system that can produce diverse speech renditions of a text by allowing (but not requiring) explicit control over the various factors of variation. We propose a new neural vocoder that offers control of such factors of variation. This is achieved by employing differentiable digital signal processing (DDSP) (previously used only for music rather than speech), which exposes these factors of variation. The results show that the proposed approach can produce natural speech with realistic timbre, and individual factors of variation can be freely controlled.