arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.04154eess.AScs.LGcs.SD
收藏

VQVC +:基于矢量量化和U-Net架构的单次语音转换

VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture

National Taiwan University(台湾大学)

Da-Yi Wu, Yen-Hao Chen, Hung-Yi Lee

摘要:

语音转换(VC)是将音频中源说话人的音色、口音和音调转换为另一个人的音色、口音和音调,同时保留语言内容的任务。这仍然是一个具有挑战性的工作,特别是在一个单一的设置。基于自动编码器的VC方法在不给出说话人身份的情况下将说话人和输入语音中的内容分离,因此这些方法可以进一步推广到看不见的说话人。解缠能力是通过矢量量化(VQ)、对抗训练或实例归一化(IN)来实现的。然而,不完美的解纠缠可能会损害输出语音的质量。在这项工作中,为了进一步提高音频质量,我们在基于自动编码器的VC系统中使用U-Net架构。我们发现,利用U-Net架构,强大的信息瓶颈是必要的。基于矢量量化的方法,量化的潜在向量,可以达到这个目的。客观和主观评价表明,该方法在音频自然度和说话人相似度方面都有较好的表现。

英文摘要:

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting. Auto-encoder-based VC methods disentangle the speaker and the content in input speech without given the speaker's identity, so these methods can further generalize to unseen speakers. The disentangle capability is achieved by vector quantization (VQ), adversarial training, or instance normalization (IN). However, the imperfect disentanglement may harm the quality of output speech. In this work, to further improve audio quality, we use the U-Net architecture within an auto-encoder-based VC system. We find that to leverage the U-Net architecture, a strong information bottleneck is necessary. The VQ-based method, which quantizes the latent vectors, can serve the purpose. The objective and the subjective evaluations show that the proposed method performs well in both audio naturalness and speaker similarity.

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。

↑