用单阶段模型实现高质量语音合成，提升自然度与说话人相似性。
Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation
- 通过语义知识蒸馏，将双阶段信息融入单阶段语音生成架构。
- 相比单阶段基线，语音质量、可懂度和说话人相似性均显著提升。
- 适合追求高效部署与高保真语音合成的应用场景。
语音标记建模已成为一种强大的语音合成框架，目前主流仍采用双阶段方法，利用语义标记。本文提出一种语义知识蒸馏方法，使单阶段模型也能实现高质量语音合成。实验表明，相较单阶段基线，该模型在语音质量、可懂度和说话人相似性方面均有提升。尽管双阶段系统在可懂度上仍占优，但本模型显著缩小了差距，同时保持相近的语音质量。结果表明，单阶段模型具备实现高效、高质量语音合成的潜力，且架构更紧凑、更易部署。
原文摘要 · Abstract (English)
Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent. In this paper, we aim to simplify this process by introducing a semantic knowledge distillation method that enables high-quality speech generation in a single stage. Our proposed model improves speech quality, intelligibility, and speaker similarity compared to a single-stage baseline. Although two-stage systems still lead in intelligibility, our model significantly narrows the gap while delivering comparable speech quality. These findings showcase the potential of single-stage models to achieve efficient, high-quality TTS with a more compact and streamlined architecture.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。