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 2302.08296cs.SDeess.AS
收藏

QuickVC:使用逆短时傅立叶变换实现任意对多语音转换

QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion

RIKEN(理化学研究所);Osaka University(大阪大学);Advanced Telecommunications Research Institute International(国际先进电信研究所)

Houjian Guo, Chaoran Liu, Carlos Toshinori Ishi, Hiroshi Ishiguro

摘要:

随着自动语音识别(ASR)和文语转换(TTS)技术的发展,通过提取源内容信息和目标说话人信息重构波形,可以实现高质量的语音转换(VC)。然而,目前的方法仍然需要改进的推理速度。在这项研究中,我们提出了一个轻量级的基于VITS的VC模型,使用的HuBERT-Soft模型提取内容信息的功能,没有说话人的信息。通过对合成语音的主观和客观实验,该模型在自然度和相似度方面表现出了竞争性的结果。重要的是,与原始的VITS模型不同,我们使用逆短时傅立叶变换(iSTFT)来替换计算成本最高的部分。实验结果表明,我们的模型可以在3090 GPU上生成超过5000 kHz的样本,在i9- 10900 K CPU上生成超过250 kHz的样本,在相同的硬件配置下实现了有竞争力的速度。

英文摘要:

With the development of automatic speech recognition (ASR) and text-to-speech (TTS) technology, high-quality voice conversion (VC) can be achieved by extracting source content information and target speaker information to reconstruct waveforms. However, current methods still require improvement in terms of inference speed. In this study, we propose a lightweight VITS-based VC model that uses the HuBERT-Soft model to extract content information features without speaker information. Through subjective and objective experiments on synthesized speech, the proposed model demonstrates competitive results in terms of naturalness and similarity. Importantly, unlike the original VITS model, we use the inverse short-time Fourier transform (iSTFT) to replace the most computationally expensive part. Experimental results show that our model can generate samples at over 5000 kHz on the 3090 GPU and over 250 kHz on the i9-10900K CPU, achieving competitive speed for the same hardware configuration.

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。

↑