MaskCycleGAN-VC：学习帧填充的非并行语音转换
MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
摘要：
非并行语音转换（VC）是一种在没有并行语料库的情况下训练语音转换器的技术。基于周期一致性对抗网络的VC（CycleGAN-VC和CycleGAN-VC 2）被广泛接受为基准方法。然而，由于他们的能力不足，把握时间-频率结构，他们的应用仅限于梅尔倒谱转换，而不是梅尔频谱转换，尽管最近在梅尔频谱声码器的进展。为了克服这一点，CycleGAN-VC 3是CycleGAN-VC 2的改进变体，它包含了一个称为时频自适应归一化（TFAN）的附加模块。然而，学习参数的数量的增加被强加。作为替代方案，我们提出了MaskCycleGAN-VC，它是CycleGAN-VC 2的另一个扩展，并使用一种称为填充帧（FIF）的新型辅助任务进行训练。使用FIF，我们将时间掩码应用于输入的梅尔频谱图，并鼓励转换器基于周围的帧填充丢失的帧。该任务允许转换器以自我监督的方式学习时频结构，并且消除了对诸如TFAN之类的附加模块的需要。对自然度和说话人相似性的主观评估表明，MaskCycleGAN-VC的性能优于CycleGAN-VC 2和CycleGAN-VC 3，模型大小与CycleGAN-VC 2相似。音频样本可在http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/maskcyclegan-vc/index.html上获得。
英文摘要：
Non-parallel voice conversion (VC) is a technique for training voice converters without a parallel corpus. Cycle-consistent adversarial network-based VCs (CycleGAN-VC and CycleGAN-VC2) are widely accepted as benchmark methods. However, owing to their insufficient ability to grasp time-frequency structures, their application is limited to mel-cepstrum conversion and not mel-spectrogram conversion despite recent advances in mel-spectrogram vocoders. To overcome this, CycleGAN-VC3, an improved variant of CycleGAN-VC2 that incorporates an additional module called time-frequency adaptive normalization (TFAN), has been proposed. However, an increase in the number of learned parameters is imposed. As an alternative, we propose MaskCycleGAN-VC, which is another extension of CycleGAN-VC2 and is trained using a novel auxiliary task called filling in frames (FIF). With FIF, we apply a temporal mask to the input mel-spectrogram and encourage the converter to fill in missing frames based on surrounding frames. This task allows the converter to learn time-frequency structures in a self-supervised manner and eliminates the need for an additional module such as TFAN. A subjective evaluation of the naturalness and speaker similarity showed that MaskCycleGAN-VC outperformed both CycleGAN-VC2 and CycleGAN-VC3 with a model size similar to that of CycleGAN-VC2. Audio samples are available at http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/maskcyclegan-vc/index.html.
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。
