论文标题
零发出的语音调节，用于降级扩散tts模型
Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models
论文作者
论文摘要
我们提出了一种新颖的方式，可以调节预验证的脱诺扩散语音模型，以在训练期间看不见的新颖人的声音产生语音。该方法需要来自目标人的短（〜3秒）样本，并且在推理时间内产生，而没有任何训练步骤。该方法的核心是采样过程，将denoising模型的估计与新扬声器样本的低通版本结合在一起。客观和主观评估表明，我们的抽样方法可以在频率方面产生与目标扬声器相似的声音，其准确性与最新方法相当，并且没有培训。
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.
