arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.03781eess.AS
收藏

基于循环一致对抗网络的情感语音转换

Emotional Voice Conversion With Cycle-consistent Adversarial Network

Songxiang Liu, Yuewen Cao, Helen Meng

摘要:

情感语音转换(Emotional Voice Conversion,简称情感语音转换)是一种将语音从一种情感状态转换为另一种情感状态的技术,它保留了说话人的基本语言信息和身份。以往的情感VC方法需要并行数据,并使用动态时间规整(DTW)方法来时间对齐源和目标语音参数。这些方法通常将最小发电损耗定义为目标函数,例如L1或L2损耗,以学习模型参数。最近,循环一致生成对抗网络(CycleGAN)已成功用于非并行VC。本文研究了使用CycleGAN进行情感VC任务的有效性。CycleGAN不是试图使用帧到帧的最小生成损失来学习并行训练数据之间的映射,而是使用两个判别器和一个分类器来指导学习过程,其中判别器旨在区分自然语音和转换语音,分类器旨在对自然语音和转换语音中的潜在情感进行分类。CycleGAN模型的训练过程将源-目标语音参数随机配对,而无需任何时间对齐操作。客观和主观评价结果证实了CycleGAN模型用于情感VC的有效性。CycleGAN的非平行训练表明它具有非平行情感VC的潜力。

英文摘要:

Emotional Voice Conversion, or emotional VC, is a technique of converting speech from one emotion state into another one, keeping the basic linguistic information and speaker identity. Previous approaches for emotional VC need parallel data and use dynamic time warping (DTW) method to temporally align the source-target speech parameters. These approaches often define a minimum generation loss as the objective function, such as L1 or L2 loss, to learn model parameters. Recently, cycle-consistent generative adversarial networks (CycleGAN) have been used successfully for non-parallel VC. This paper investigates the efficacy of using CycleGAN for emotional VC tasks. Rather than attempting to learn a mapping between parallel training data using a frame-to-frame minimum generation loss, the CycleGAN uses two discriminators and one classifier to guide the learning process, where the discriminators aim to differentiate between the natural and converted speech and the classifier aims to classify the underlying emotion from the natural and converted speech. The training process of the CycleGAN models randomly pairs source-target speech parameters, without any temporal alignment operation. The objective and subjective evaluation results confirm the effectiveness of using CycleGAN models for emotional VC. The non-parallel training for a CycleGAN indicates its potential for non-parallel emotional VC.

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。

↑