Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Zhang, Zewang"'
WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial Training
This paper aims to introduce a robust singing voice synthesis (SVS) system to produce very natural and realistic singing voices efficiently by leveraging the adversarial training strategy. On one hand, we designed simple but generic random area condi
Externí odkaz:
http://arxiv.org/abs/2207.01886
In this paper, we develop a new multi-singer Chinese neural singing voice synthesis (SVS) system named WeSinger. To improve the accuracy and naturalness of synthesized singing voice, we design several specifical modules and techniques: 1) A deep bi-d
Externí odkaz:
http://arxiv.org/abs/2203.10750
Autor:
Hai, Zhenyin, Su, Zhixuan, Guo, Maocheng, Chen, Jun, Lin, Runze, Chen, Yue, Zhang, Yihang, Zhu, Hongtian, Liang, Rui, Gong, Shigui, Wang, Zihan, Li, Junyang, Zhang, ZeWang, Xue, Chenyang
Publikováno v:
In Measurement 15 January 2025 239
Autor:
Zhang, Zewang, Chen, Gonglei, Yu, Xiangyang, Liang, Dong, Xu, Cong, Ji, Cheng, Wang, Lei, Ma, Hongbo, Wang, Jidong
Publikováno v:
In Science of the Total Environment 1 January 2024 906
Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast and stable. However, the quality
Externí odkaz:
http://arxiv.org/abs/2011.12206
Autor:
Tian, Qiao, Zhang, Zewang, Liu, Chao, Lu, Heng, Chen, Linghui, Wei, Bin, He, Pujiang, Liu, Shan
Attention based neural TTS is elegant speech synthesis pipeline and has shown a powerful ability to generate natural speech. However, it is still not robust enough to meet the stability requirements for industrial products. Besides, it suffers from s
Externí odkaz:
http://arxiv.org/abs/2011.00935
This paper investigates how to leverage a DurIAN-based average model to enable a new speaker to have both accurate pronunciation and fluent cross-lingual speaking with very limited monolingual data. A weakness of the recently proposed end-to-end text
Externí odkaz:
http://arxiv.org/abs/2005.05642
In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear predictive charact
Externí odkaz:
http://arxiv.org/abs/2005.05551
Autor:
Zhang, Zewang, Yang, Shuo, Wu, Yi-hang, Liu, Chenxi, Han, Yimin, Lee, Ching Hua, Sun, Zheng, Li, Guangjie, Zhang, Xiao
Machine learning (ML) architectures such as convolutional neural networks (CNNs) have garnered considerable recent attention in the study of quantum many-body systems. However, advanced ML approaches such as transfer learning have seldom been applied
Externí odkaz:
http://arxiv.org/abs/1905.09168
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.