arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.00992cs.SDcs.AIeess.AS
收藏

NVC-Net:端到端对抗语音转换

NVC-Net: End-to-End Adversarial Voice Conversion

Sony Europe B.V.(索尼欧洲公司)

Bac Nguyen, Fabien Cardinaux

摘要:

在语音合成的许多应用中,语音转换越来越受欢迎。这个想法是改变语音身份从一个发言者到另一个,同时保持语言内容不变。许多语音转换方法依赖于使用声码器来从声学特征重构语音,因此,语音质量在很大程度上取决于这样的声码器。在本文中,我们提出了NVC-Net,这是一种端到端的对抗网络,它直接对任意长度的原始音频波形进行语音转换。通过从语音内容中分离出说话者身份,NVC-Net能够执行非并行的传统多对多语音转换以及从看不见的目标说话者的短话语中进行zero-shot语音转换。重要的是,NVC-Net是非自回归和完全卷积的,可以实现快速推理。我们的模型能够在NVIDIA V100 GPU上以超过3600 kHz的速率生成样本,在相同的硬件配置下比最先进的方法快几个数量级。非并行多对多语音转换任务的客观和主观评价表明,NVC-Net获得了具有竞争力的结果,具有显着更少的参数。

英文摘要:

Voice conversion has gained increasing popularity in many applications of speech synthesis. The idea is to change the voice identity from one speaker into another while keeping the linguistic content unchanged. Many voice conversion approaches rely on the use of a vocoder to reconstruct the speech from acoustic features, and as a consequence, the speech quality heavily depends on such a vocoder. In this paper, we propose NVC-Net, an end-to-end adversarial network, which performs voice conversion directly on the raw audio waveform of arbitrary length. By disentangling the speaker identity from the speech content, NVC-Net is able to perform non-parallel traditional many-to-many voice conversion as well as zero-shot voice conversion from a short utterance of an unseen target speaker. Importantly, NVC-Net is non-autoregressive and fully convolutional, achieving fast inference. Our model is capable of producing samples at a rate of more than 3600 kHz on an NVIDIA V100 GPU, being orders of magnitude faster than state-of-the-art methods under the same hardware configurations. Objective and subjective evaluations on non-parallel many-to-many voice conversion tasks show that NVC-Net obtains competitive results with significantly fewer parameters.

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。

↑