Recent Development of the DNN-based Singing Voice Synthesis System — Sinsy
Recent Development of the DNN-based Singing Voice Synthesis System — Sinsy
复制标题
DOI：
10.23919/apsipa.2018.8659797
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Keiichiro Oura;Ayami Mase;T. Yamada;Satoru Muto;Yoshihiko Nankaku;K. Tokuda
中科院分区：
文献类型：
--
作者：
Keiichiro Oura;Ayami Mase;T. Yamada;Satoru Muto;Yoshihiko Nankaku;K. Tokuda
介绍了一种基于深度神经网络的歌唱语音合成系统SINSY。基于隐马尔可夫模型(HMM)的歌唱语音合成系统在过去的十年中得到了发展。近年来，人们提出了基于DNN的歌唱语音合成系统。它提高了合成歌声的自然度。本文将轨迹训练、颤音模型和时滞模型等技术引入到基于DNN的歌唱语音合成系统中，以合成高质量的歌唱语音。实验结果表明，采用这些技术的基于DNN的系统比基于HMM的系统性能更好。此外，本文还详细介绍了歌唱语音合成的在线服务。
This paper describes a singing voice synthesis system based on deep neural networks (DNNs) named Sinsy. Singing voice synthesis systems based on hidden Markov models (HMMs) have grown in the last decade. Recently, singing voice synthesis systems based on DNNs have been proposed. It has improved the naturalness of the synthesized singing voices. In this paper, we introduce several techniques, i.e., trajectory training, a vibrato model, and a time-lag model, into the DNN-based singing voice synthesis system to synthesize the high quality singing voices. Experimental results show that the DNN-based systems with these techniques outperformed the HMM-based systems. In addition, the present paper describes the details of the on-line service for singing voice synthesis.