Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models

Understand

We present a novel way of conditioning a pretrained denoising diffusion speech model to produce speech in the voice of a novel person unseen during training.

• The method requires a short (~3 seconds) sample from the target person, and generation is steered at inference time, without any training steps.
• At the heart of the method lies a sampling process that combines the estimation of the denoising model with a low-pass version of the new speaker's sample.
• The objective and subjective evaluations show that our sampling method can generate a voice similar to that of the target speaker in terms of frequency, with an accuracy comparable to state-of-the-art methods, and without training.