arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09378eess.AScs.SD
收藏

MobileSpeech:一个用于移动端零样本文本到语音的快速高保真框架

MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech

Zhejiang University(浙江大学);Shanghai AI Laboratory(上海人工智能实验室)

Shengpeng Ji, Ziyue Jiang, Hanting Wang, Jialong Zuo, Zhou Zhao

AI总结:

本文提出MobileSpeech,首个基于移动设备的快速、轻量且鲁棒的零样本文本到语音框架,通过并行语音掩码解码器与高层概率掩码实现高保真与高生成速度。

摘要:

零样本文本到语音(TTS)因其强大的语音克隆能力而备受关注,仅需几秒钟未见过的说话人语音提示。然而,以往所有工作均基于云端系统开发。以自回归模型为例,尽管这些方法实现了高保真语音克隆,但在推理速度、模型大小和鲁棒性方面存在不足。因此,我们提出了MobileSpeech,这是首次基于移动设备构建的快速、轻量且鲁棒的零样本文本到语音系统。具体而言:1)利用离散编解码器,我们设计了一个名为SMD的并行语音掩码解码器模块,该模块在生成过程中融合了语音编解码器的分层信息以及不同编解码器层间的权重机制。此外,为弥合文本与语音之间的差距,我们引入了高层概率掩码,模拟语音生成中信息流由少到多的推进过程。2)针对说话人提示,我们从提示语音中提取细粒度的提示时长,并通过SMD中的交叉注意力融合文本和提示语音。我们在不同级别的多语言数据集上验证了MobileSpeech的有效性,在生成速度和语音质量方面达到了最先进水平。MobileSpeech在单块A100 GPU上实现了0.09的RTF,并已成功部署于移动设备。

英文摘要:

Zero-shot text-to-speech (TTS) has gained significant attention due to its powerful voice cloning capabilities, requiring only a few seconds of unseen speaker voice prompts. However, all previous work has been developed for cloud-based systems. Taking autoregressive models as an example, although these approaches achieve high-fidelity voice cloning, they fall short in terms of inference speed, model size, and robustness. Therefore, we propose MobileSpeech, which is a fast, lightweight, and robust zero-shot text-to-speech system based on mobile devices for the first time. Specifically: 1) leveraging discrete codec, we design a parallel speech mask decoder module called SMD, which incorporates hierarchical information from the speech codec and weight mechanisms across different codec layers during the generation process. Moreover, to bridge the gap between text and speech, we introduce a high-level probabilistic mask that simulates the progression of information flow from less to more during speech generation. 2) For speaker prompts, we extract fine-grained prompt duration from the prompt speech and incorporate text, prompt speech by cross attention in SMD. We demonstrate the effectiveness of MobileSpeech on multilingual datasets at different levels, achieving state-of-the-art results in terms of generating speed and speech quality. MobileSpeech achieves RTF of 0.09 on a single A100 GPU and we have successfully deployed MobileSpeech on mobile devices. Audio samples are available at \url{https://mobilespeech.github.io/} .

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。

↑