DualSpeech：通过双重无分类器引导增强说话人保真度与文本可懂度
DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance
AI总结：
DualSpeech提出一种结合音素级潜在扩散与双重无分类器引导的TTS模型，有效平衡了说话人保真度与文本可懂度，并在性能上超越现有最先进方法。
摘要：
文本转语音（TTS）模型已取得显著进展，旨在准确复制人类语音的多样性，包括独特的说话人身份和语言细微差别。尽管取得了这些进展，实现说话人保真度与文本可懂度之间的最佳平衡仍是一项挑战，尤其是在考虑多样化控制需求时。为解决此问题，我们提出了DualSpeech，这是一种将音素级潜在扩散与双重无分类器引导相结合的TTS模型。该方法能够对说话人保真度与文本可懂度实现卓越控制。实验结果表明，通过利用这种精细控制，DualSpeech在性能上超越了现有的最先进TTS模型。演示请见 https://bit.ly/48Ewoib。
英文摘要：
Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between speaker-fidelity and text-intelligibility remains a challenge, particularly when diverse control demands are considered. Addressing this, we introduce DualSpeech, a TTS model that integrates phoneme-level latent diffusion with dual classifier-free guidance. This approach enables exceptional control over speaker-fidelity and text-intelligibility. Experimental results demonstrate that by utilizing the sophisticated control, DualSpeech surpasses existing state-of-the-art TTS models in performance. Demos are available at https://bit.ly/48Ewoib.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
