基于掩码循环一致生成对抗网络的无声语音免声码器非平行转换
Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks
AI总结：
本研究提出一种免声码器的统一模型，结合循环一致训练与自监督任务，实现非平行耳语语音转换，主观测试显示相对基线提升达6.7%。
摘要：
循环一致生成对抗网络已广泛用于非平行语音转换（VC）。它们能够在无需平行训练数据的情况下学习源特征与目标特征之间的映射，从而消除了对时间对齐的需求。然而，大多数方法通过使用单独的转换模型和波形合成模型，将声学特征的转换与音频信号的合成解耦。本研究将转换与合成统一到单一模型中，从而无需单独的声码器。通过利用循环一致训练和自监督辅助训练任务，我们的模型能够高效地生成转换后的高质量原始音频波形。主观听力测试表明，我们的统一方法在耳语语音转换中相对于基线实现了高达6.7%的改进。平均意见得分预测在常规语音转换中也产生了稳定的结果（相对改进在0.5%至2.4%之间）。
英文摘要：
Cycle-consistent generative adversarial networks have been widely used in non-parallel voice conversion (VC). Their ability to learn mappings between source and target features without relying on parallel training data eliminates the need for temporal alignments. However, most methods decouple the conversion of acoustic features from synthesizing the audio signal by using separate models for conversion and waveform synthesis. This work unifies conversion and synthesis into a single model, thereby eliminating the need for a separate vocoder. By leveraging cycle-consistent training and a self-supervised auxiliary training task, our model is able to efficiently generate converted high-quality raw audio waveforms. Subjective listening tests showed that our unified approach achieved improvements of up to 6.7% relative to the baseline in whispered VC. Mean opinion score predictions also yielded stable results in conventional VC (between 0.5% and 2.4% relative improvement).
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。
