Non-parallel voice conversion (VC) is a technique for learning the mapping
from source to target speech without relying on parallel data. This is an
important task, but it has been challenging due to the disadvantages of the
training conditions. Recently, CycleGAN-VC has provided a breakthrough and
performed comparably to a parallel VC method without relying on any extra data,
modules, or time alignment procedures. However, there is still a large gap
between the real target and converted speech, and bridging this gap remains a
challenge. To reduce this gap, we propose CycleGAN-VC2, which is an improved
version of CycleGAN-VC incorporating three new techniques: an improved
objective (two-step adversarial losses), improved generator (2-1-2D CNN), and
improved discriminator (PatchGAN). We evaluated our method on a non-parallel VC
task and analyzed the effect of each technique in detail. An objective
evaluation showed that these techniques help bring the converted feature
sequence closer to the target in terms of both global and local structures,
which we assess by using Mel-cepstral distortion and modulation spectra
distance, respectively. A subjective evaluation showed that CycleGAN-VC2
outperforms CycleGAN-VC in terms of naturalness and similarity for every
speaker pair, including intra-gender and inter-gender pairs.

本文提出了 CycleGAN-VC2，它是 CycleGAN-VC 的改进版本，加入了三种新技术：改进的目标函数（两步对抗性损失）、改进的生成器（2-1-2D CNN）和改进的鉴别器（PatchGAN），经过客观和主观评估，表明 CycleGAN-VC2 在语音转换任务中具有更接近目标的特征序列，且自然度和相似度更好。