arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.12604eess.ASstat.ML
收藏

基于增强分类器星形生成对抗网络的非并行语音转换

Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks

Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo

摘要:

我们之前提出了一种方法,通过使用一种名为StarGAN的生成对抗网络(GANs)的变体来实现非并行语音转换(VC)。我们的方法称为StarGAN-VC,其主要特点如下:首先,它不需要并行的话语,transmittance或时间对齐程序来进行语音生成器训练。其次,它可以使用单个生成器网络同时学习跨多个域的映射,从而充分利用从多个域收集的可用训练数据来捕获所有域共有的潜在特征。第三,它可以足够快地生成转换后的语音信号,以允许实时实现,并且只需要几分钟的训练示例就可以生成相当逼真的语音。在本文中,我们描述了三个配方的StarGAN,包括一个新推出的新的StarGAN变体称为“增强分类器StarGAN(A-StarGAN)”,并比较它们在非并行VC任务。我们还将它们与几种基线方法进行了比较。

英文摘要:

We previously proposed a method that allows for nonparallel voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of our method, called StarGAN-VC, are as follows: First, it requires no parallel utterances, transcriptions, or time alignment procedures for speech generator training. Second, it can simultaneously learn mappings across multiple domains using a single generator network and thus fully exploit available training data collected from multiple domains to capture latent features that are common to all the domains. Third, it can generate converted speech signals quickly enough to allow real-time implementations and requires only several minutes of training examples to generate reasonably realistic-sounding speech. In this paper, we describe three formulations of StarGAN, including a newly introduced novel StarGAN variant called "Augmented classifier StarGAN (A-StarGAN)", and compare them in a nonparallel VC task. We also compare them with several baseline methods.

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。

↑