arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.03377cs.SDeess.AS
收藏

基于模型编辑的特征语音合成用于说话人生成

Eigenvoice Synthesis based on Model Editing for Speaker Generation

CyberAgentJapan(CyberAgent日本);Nagoya University(名古屋大学)

Masato Murata, Koichi Miyazaki, Tomoki Koriyama, Tomoki Toda

AI总结:

本文提出基于DNN模型编辑的特征语音合成方法,在模型参数空间中定义说话人空间并采样生成多样化语音,实验验证其有效性并发现性别主导轴。

摘要:

说话人生成任务旨在无需参考语音即可创建未见过的说话人声音。该任务的关键在于定义一个能够表示多样化说话人的说话人空间,以确定生成说话人的特征。然而,定义这一说话人空间的有效方法仍不明确。特征语音合成是传统参数合成框架(如基于HMM的方法)中一种有前景的方法,它利用预存储的说话人特征来定义低维说话人空间。本研究提出了一种新颖的基于DNN的、通过模型编辑实现的特征语音合成方法。与先前方法不同,我们的方法在DNN模型参数空间中定义说话人空间。通过在该空间中直接采样新的DNN模型参数,我们可以创建多样化的说话人声音。实验结果表明,我们的方法具备生成多样化说话人语音的能力。此外,我们在所创建的说话人空间中发现了性别主导轴,这表明了控制说话人属性的潜力。

英文摘要:

Speaker generation task aims to create unseen speaker voice without reference speech. The key to the task is defining a speaker space that represents diverse speakers to determine the generated speaker trait. However, the effective way to define this speaker space remains unclear. Eigenvoice synthesis is one of the promising approaches in the traditional parametric synthesis framework, such as HMM-based methods, which define a low-dimensional speaker space using pre-stored speaker features. This study proposes a novel DNN-based eigenvoice synthesis method via model editing. Unlike prior methods, our method defines a speaker space in the DNN model parameter space. By directly sampling new DNN model parameters in this space, we can create diverse speaker voices. Experimental results showed the capability of our method to generate diverse speakers' speech. Moreover, we discovered a gender-dominant axis in the created speaker space, indicating the potential to control speaker attributes.

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。

↑