Zobrazeno 1 - 10
of 1 612
pro vyhledávání: '"LU Quan"'
Trained on 680,000 hours of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior performance in automatic speech recognition, translation, and language identification. However, its applicability
Externí odkaz:
http://arxiv.org/abs/2407.10048
Autor:
Chen, Zhigang, Zhou, Benjia, Li, Jun, Wan, Jun, Lei, Zhen, Jiang, Ning, Lu, Quan, Zhao, Guoqing
Previous Sign Language Translation (SLT) methods achieve superior performance by relying on gloss annotations. However, labeling high-quality glosses is a labor-intensive task, which limits the further development of SLT. Although some approaches wor
Externí odkaz:
http://arxiv.org/abs/2403.12556
Autor:
Han, Runduo, Yan, Xiaopeng, Xu, Weiming, Guo, Pengcheng, Sun, Jiayao, Wang, He, Lu, Quan, Jiang, Ning, Xie, Lei
This paper describes our audio-quality-based multi-strategy approach for the audio-visual target speaker extraction (AVTSE) task in the Multi-modal Information based Speech Processing (MISP) 2023 Challenge. Specifically, our approach adopts different
Externí odkaz:
http://arxiv.org/abs/2401.03697
Dynamic NeRFs have recently garnered growing attention for 3D talking portrait synthesis. Despite advances in rendering speed and visual quality, challenges persist in enhancing efficiency and effectiveness. We present R2-Talker, an efficient and eff
Externí odkaz:
http://arxiv.org/abs/2312.05572
Autor:
Han, Tianshun, Gui, Shengnan, Huang, Yiqing, Li, Baihui, Liu, Lijian, Zhou, Benjia, Jiang, Ning, Lu, Quan, Zhi, Ruicong, Liang, Yanyan, Zhang, Du, Wan, Jun
Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argu
Externí odkaz:
http://arxiv.org/abs/2312.02781
Publikováno v:
Zhishi guanli luntan, Vol 6, Iss 6, Pp 0-0 (2021)
[Purpose/significance] This research explores the relationship between the health information search behaviors of college students and the spatiotemporal situation of public health emergencies, in order to reveal the coupling characteristics of users
Externí odkaz:
https://doaj.org/article/64fa9b7b7aa3428b8dfb00d9b3602cdd
Publikováno v:
Cailiao gongcheng, Vol 45, Iss 11, Pp 96-101 (2017)
In view of the problem that paste flux is difficult to spread uniformly on the surface of filler metal, the adhesion behavior of the different concentrations of paste flux on the surface of filler metal was studied by the equipment of OM, wetting ang
Externí odkaz:
https://doaj.org/article/0213fdd192024340aa2ecf93f560ebbb
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
Automatic Speech Recognition (ASR) in conversational settings presents unique challenges, including extracting relevant contextual information from previous conversational turns. Due to irrelevant content, error propagation, and redundancy, existing
Externí odkaz:
http://arxiv.org/abs/2310.14278
Publikováno v:
Cailiao gongcheng, Vol 44, Iss 6, Pp 17-23 (2016)
The Al-Si-Cu alloy system is considered to be a promising choice of filler metal for aluminium alloys brazing due to its high strength and low melting point. The greatest obstacle is its lack of plastic forming ability and being difficult to be proce
Externí odkaz:
https://doaj.org/article/27e749c7a1cc40bdbf6cdbc45262bf41
Autor:
Tang, Hui-bo, Yu-fei, Hao, Hu, Guang-yue, Lu, Quan-ming, Ren, Chuang, Zhang, Yu, Guo, Ao, Hu, Peng, Wang, Yu-lin, Wang, Xiang-bing, Zhang, Zhen-chi, Yuan, Peng, Liu, Wei, Si, Hua-chong, Yu, Chun-kai, Zhao, Jia-yi, Wang, Jin-can, Zhang, Zhe, Yuan, Xiao-hui, Yuan, Da-wei, Xie, Zhi-yong, Xiong, Jun, Fang, Zhi-heng, Xu, Jian-cai, Ju, Jing-Jing, Guo-qiang, Zhang, Zhu, Jian-Qiang, Shen, Bai-fei, Li, Ru-xin, Xu, Zhi-zhan
Fermi acceleration by collisionless shocks is believed to be the primary mechanism to produce high energy charged particles in the Universe,where charged particles gain energy successively from multiple reflections off the shock front.Here,we present
Externí odkaz:
http://arxiv.org/abs/2211.03090