arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20113cs.SDcs.AI
收藏

StyleStream: 实时零样本语音风格转换

StyleStream: Real-Time Zero-Shot Voice Style Conversion

UC Berkeley(伯克利大学)

Yisi Liu, Nicholas Lee, Gopala Anumanchipalli

AI总结:

StyleStream通过Destylizer和Stylizer实现实时零样本语音风格转换,采用非自回归架构,端到端延迟仅1秒。

摘要:

语音风格转换旨在将输入语句转换为目标说话人的音色、口音和情感,其核心挑战是将语言内容与风格解耦。尽管已有研究探索了这一问题,但转换质量仍然有限,且实时语音风格转换尚未得到解决。我们提出了StyleStream,这是首个可流式传输的零样本语音风格转换系统,实现了最先进的性能。StyleStream由两个组件组成:Destylizer,用于在保留语言内容的同时去除风格属性;Stylizer是一种扩散变压器(DiT),根据参考语音重新引入目标风格。通过文本监督和高度约束的信息瓶颈,实现了稳健的内容-风格解耦。这种设计使得系统能够完全非自回归地运行,实现实时语音风格转换,端到端延迟仅为1秒。样本和实时演示:https://berkeley-speech-group.github.io/StyleStream/。

英文摘要:

Voice style conversion aims to transform an input utterance to match a target speaker's timbre, accent, and emotion, with a central challenge being the disentanglement of linguistic content from style. While prior work has explored this problem, conversion quality remains limited, and real-time voice style conversion has not been addressed. We propose StyleStream, the first streamable zero-shot voice style conversion system that achieves state-of-the-art performance. StyleStream consists of two components: a Destylizer, which removes style attributes while preserving linguistic content, and a Stylizer, a diffusion transformer (DiT) that reintroduces target style conditioned on reference speech. Robust content-style disentanglement is enforced through text supervision and a highly constrained information bottleneck. This design enables a fully non-autoregressive architecture, achieving real-time voice style conversion with an end-to-end latency of 1 second. Samples and real-time demo: https://berkeley-speech-group.github.io/StyleStream/.

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。

↑