基于去噪扩散概率GAN模型的语音转换
Voice Conversion with Denoising Diffusion Probabilistic GAN Models
AI总结：
针对GAN生成语音多样性不足、DDPM推理慢的问题，提出结合两者的DiffGAN-VC模型，采用大步长去噪与多模态条件GAN，实现非平行多对多语音转换，在音质、说话人相似度和自然度上优于CycleGAN-VC。
摘要：
语音转换是一种在保持语言信息完整性的前提下转换说话风格的方法。目前已有众多研究者将深度生成模型用于语音转换任务：生成对抗网络（GANs）可快速生成高质量样本，但生成样本缺乏多样性；去噪扩散概率模型（DDPMs）生成的样本在模式覆盖度和样本多样性上优于GANs，但计算成本高、推理速度慢于GANs。为提升GANs与DDPMs的实用性，本文提出DiffGAN-VC——一种结合GANs与DDPMs的变体模型，用于实现非平行多对多语音转换（VC）。该方法采用大步长实现去噪，同时引入多模态条件GANs对去噪扩散生成对抗网络进行建模。主客观评估实验表明，DiffGAN-VC在非平行数据集上可实现高语音质量；与CycleGAN-VC方法相比，DiffGAN-VC在说话人相似度、自然度方面表现更优，且音质更高。
英文摘要：
Voice conversion is a method that allows for the transformation of speaking style while maintaining the integrity of linguistic information. There are many researchers using deep generative models for voice conversion tasks. Generative Adversarial Networks (GANs) can quickly generate high-quality samples, but the generated samples lack diversity. The samples generated by the Denoising Diffusion Probabilistic Models (DDPMs) are better than GANs in terms of mode coverage and sample diversity. But the DDPMs have high computational costs and the inference speed is slower than GANs. In order to make GANs and DDPMs more practical we proposes DiffGAN-VC, a variant of GANs and DDPMS, to achieve non-parallel many-to-many voice conversion (VC). We use large steps to achieve denoising, and also introduce a multimodal conditional GANs to model the denoising diffusion generative adversarial network. According to both objective and subjective evaluation experiments, DiffGAN-VC has been shown to achieve high voice quality on non-parallel data sets. Compared with the CycleGAN-VC method, DiffGAN-VC achieves speaker similarity, naturalness and higher sound quality.
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。
