Implementation of DNN-based real-time voice conversion and its improvements by audio data augmentation and mask-shaped device
Implementation of DNN-based real-time voice conversion and its improvements by audio data augmentation and mask-shaped device
复制标题
基于DNN的实时语音转换的实现及其通过音频数据增强和掩模形装置的改进
DOI：
10.21437/ssw.2019-17
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
H. Saruwatari
中科院分区：
文献类型：
--
作者：
Riku Arakawa;Shinnosuke Takamichi;H. Saruwatari
语音转换（VC）使我们能够在保留语言信息的情况下改变语音，有望在增强人类交流中发挥重要作用。近年来，基于深度神经网络（deep neural network， DNN）的VC因能够合成高质量语音而备受关注。然而，现有的方法通常假设离线过程（即分析、转换和合成），不能直接应用于实时VC。因此，我们提出了一种基于dnn的低延迟在线VC实现方法。为了提高实时VC的语音质量，我们还提出了音频数据增强的方法。最后，我们开发了一个基于掩模的实时VC设备，以提高对背景噪声的鲁棒性。实验结果表明：1)所提出的实时VC的实时性因子为0.50;2)所提出的数据增强方法提高了语音质量；3)所提出的基于掩模的VC设备比基于标准麦克风的VC设备对噪声的鲁棒性更强。
Voice conversion (VC) enables us to change speech while preserving the linguistic information and is expected to play a significant role in augmented human communication. Recently, deep neural network (DNN)-based VC has been attracting attention because it can synthesize high-quality speech. However, existing methods typically assume offline processes (i.e., analysis, conversion, and synthesis) and cannot be directly applied to real-time VC. Therefore, we propose an implementation method of DNN-based VC that works online with low latency. We also propose audio data augmentation to improve the speech quality of real-time VC. Finally, we develop a mask-based real-time VC device to improve robustness against background noise. Experimental results demonstrate that 1) the proposed real-time VC works with 0.50 of the real-time factor, 2) the proposed data augmentation improves speech quality, and 3) the proposed mask-based VC device is more robust to noise than a standard microphone-based VC device.
DOI：
10.1109/icassp.2013.6639215
发表时间：
2013-05
期刊：
2013 IEEE International Conference on Acoustics, Speech and Signal Processing
影响因子：
--
作者：
H. Zen;A. Senior;M. Schuster
通讯作者：
H. Zen;A. Senior;M. Schuster
(2008) 历史和地理过程导致介壳虫的多样化，这些介壳虫与蚂蚁植物马卡兰加 (Macaranga) 共生。
DOI：
--
发表时间：
2008
期刊：
影响因子：
--
作者：
上田昇平・Quek;S.-P.・市岡孝朗・村瀬香・Kondo;T・Gullan;P. J.・市野隆雄
通讯作者：
P. J.・市野隆雄