VoiceTailor：用于基于扩散的个性化文本到语音的轻量级插件适配器
VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech
AI总结：
VoiceTailor通过在预训练扩散TTS模型中结合LoRA适配器与指导技术，仅微调0.25%参数即实现与现有模型相当的说话人自适应性能及强鲁棒性。
摘要：
我们提出了VoiceTailor，一个参数高效的说话人自适应文本到语音（TTS）系统，通过为预训练的基于扩散的TTS模型配备个性化适配器。VoiceTailor基于权重变化比率分析，识别出能从适配器中受益的关键模块。我们利用低秩适应（LoRA）作为参数高效适应方法，并将适配器整合到预训练扩散解码器的关键模块中。为在少量参数下实现强大的适应性能，我们探索了多种用于说话人适应的指导技术，并研究了增强说话人信息的最佳策略。仅微调0.25%的总参数，VoiceTailor展现出与现有自适应TTS模型相当的说话人适应性能。如演示所示，VoiceTailor在适应广泛的现实世界说话人时表现出强大的鲁棒性。
英文摘要：
We propose VoiceTailor, a parameter-efficient speaker-adaptive text-to-speech (TTS) system, by equipping a pre-trained diffusion-based TTS model with a personalized adapter. VoiceTailor identifies pivotal modules that benefit from the adapter based on a weight change ratio analysis. We utilize Low-Rank Adaptation (LoRA) as a parameter-efficient adaptation method and incorporate the adapter into pivotal modules of the pre-trained diffusion decoder. To achieve powerful adaptation performance with few parameters, we explore various guidance techniques for speaker adaptation and investigate the best strategies to strengthen speaker information. VoiceTailor demonstrates comparable speaker adaptation performance to existing adaptive TTS models by fine-tuning only 0.25\% of the total parameters. VoiceTailor shows strong robustness when adapting to a wide range of real-world speakers, as shown in the demo.
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。
