Zobrazeno 1 - 10
of 303
pro vyhledávání: '"Chen, Feiyang"'
Autor:
Yang, Qian, Zuo, Jialong, Su, Zhe, Jiang, Ziyue, Li, Mingze, Zhao, Zhou, Chen, Feiyang, Wang, Zhefeng, Huai, Baoxing
We introduce an open source high-quality Mandarin TTS dataset MSceneSpeech (Multiple Scene Speech Dataset), which is intended to provide resources for expressive speech synthesis. MSceneSpeech comprises numerous audio recordings and texts performed a
Externí odkaz:
http://arxiv.org/abs/2407.14006
This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, navigating the game's complex dyn
Externí odkaz:
http://arxiv.org/abs/2407.13943
Publikováno v:
Journal of Information, Technology and Policy (2024): 1-12
Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study addresses the
Externí odkaz:
http://arxiv.org/abs/2404.10407
Autor:
Zhang, Yu, Huang, Rongjie, Li, Ruiqi, He, JinZheng, Xia, Yan, Chen, Feiyang, Duan, Xinyu, Huai, Baoxing, Zhao, Zhou
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence, 38(17), 19597-19605. (2024)
Style transfer for out-of-domain (OOD) singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles (such as timbre, emotion, pronunciation, and articulation skills) derived from reference singing voice samples.
Externí odkaz:
http://arxiv.org/abs/2312.10741
Autor:
Ji, Shengpeng, Zuo, Jialong, Fang, Minghui, Jiang, Ziyue, Chen, Feiyang, Duan, Xinyu, Huai, Baoxing, Zhao, Zhou
Publikováno v:
2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Recently, there has been a growing interest in the field of controllable Text-to-Speech (TTS). While previous studies have relied on users providing specific style factor values based on acoustic knowledge or selecting reference speeches that meet ce
Externí odkaz:
http://arxiv.org/abs/2308.14430
Autor:
Xiao, Xiong, Xu, Guojun, Lai, Qiang, Jin, Chenxin, Wan, Yan, Chen, Feiyang, Sun, Fugen, Li, Yong, Zhou, Lang, Yue, Zhihao
Publikováno v:
In Electrochimica Acta 10 October 2024 501
Publikováno v:
In Gondwana Research October 2024 134:209-221
Publikováno v:
In Infrared Physics and Technology September 2024 141
Publikováno v:
In Computers and Chemical Engineering September 2024 188
Publikováno v:
In Pattern Recognition February 2025 158