3 code implementations • 9 May 2022 • Xu Tan, Jiawei Chen, Haohe Liu, Jian Cong, Chen Zhang, Yanqing Liu, Xi Wang, Yichong Leng, YuanHao Yi, Lei He, Frank Soong, Tao Qin, Sheng Zhao, Tie-Yan Liu
In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset.
Ranked #1 on Text-To-Speech Synthesis on LJSpeech (using extra training data)
no code implementations • 17 Oct 2021 • Yongmao Zhang, Jian Cong, Heyang Xue, Lei Xie, Pengcheng Zhu, Mengxiao Bi
In this paper, we propose VISinger, a complete end-to-end high-quality singing voice synthesis (SVS) system that directly generates audio waveform from lyrics and musical score.
no code implementations • 21 Jun 2021 • Jian Cong, Shan Yang, Lei Xie, Dan Su
Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the intermediate representation.
no code implementations • 21 Jun 2021 • Jian Cong, Shan Yang, Na Hu, Guangzhi Li, Lei Xie, Dan Su
Specifically, we use explicit labels to represent two typical spontaneous behaviors filled-pause and prolongation in the acoustic model and develop a neural network based predictor to predict the occurrences of the two behaviors from text.