为了解决这个问题,我们提出了CycleGAN-VC3,它是CycleGANVC2的改进,它结合了时频自适应归一化(TFAN)。 使用TFAN,我们可以调整转换特征的比例和偏差,同时反映源Mel频谱图的时频结构。 我们在性别间和性别内非平行VC上评估了CycleGAN-VC3。 对自然性和相似性的主观评估表明,对于每个VC对,CycleGAN-VC3的性能均优于或优...
structure of the source mel-spectrogram. We evaluated CycleGAN-VC3 on inter-gender and intra-gender non-parallel VC. A subjective evaluation of naturalness and similarity showed that for every VC pair, CycleGAN-VC3 outperforms or is competitive with the two types of CycleGAN-VC2, one of which ...
CycleGAN-VC3-PyTorch | 该代码是PyTorch的纸上实现: ,这是有关语音转换/语音克隆的工作。 数据集 风投 用法 训练 例子 演示版 参考 循环GAN-VC3 非并行语音转换(VC)是一种无需使用并行语料库即可学习源语音和目标语音之间的映射的技术。 最近,CycleGAN-VC [3]和CycleGAN-VC2 [2]在此问题上已经显示出令人...
To remedy this, we propose CycleGAN-VC3, an improvement of CycleGAN-VC2 that incorporates time-frequency adaptive normalization (TFAN). Using TFAN, we can adjust the scale and bias of the converted features while reflecting the time-frequency structure of the source mel-spectrogram. We evaluated...