Zobrazeno 1 - 10
of 2 815
pro vyhledávání: '"Yang, Mu"'
Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation
Current leading Text-To-Audio (TTA) generation models suffer from degraded performance on zero-shot and few-shot settings. It is often challenging to generate high-quality audio for audio events that are unseen or uncommon in the training set. Inspir
Externí odkaz:
http://arxiv.org/abs/2411.05141
Autor:
Wang, Xiyang, Qi, Shouzheng, Zhao, Jieyou, Zhou, Hangning, Zhang, Siyu, Wang, Guoan, Tu, Kai, Guo, Songlin, Zhao, Jianbo, Li, Jian, Yang, Mu
This paper introduces MCTrack, a new 3D multi-object tracking method that achieves state-of-the-art (SOTA) performance across KITTI, nuScenes, and Waymo datasets. Addressing the gap in existing tracking paradigms, which often perform well on specific
Externí odkaz:
http://arxiv.org/abs/2409.16149
Autor:
Zheng, Yi, Liu, Zhao-Di, Miao, Rui-Heng, Cui, Jin-Ming, Yang, Mu, Xu, Xiao-Ye, Xu, Jin-Shi, Li, Chuan-Feng, Guo, Guang-Can
Publikováno v:
Phys. Rev. Lett. 133, 033602 (2024)
With an extremely high dimensionality, the spatial degree of freedom of entangled photons is a key tool for quantum foundation and applied quantum techniques. To fully utilize the feature, the essential task is to experimentally characterize the mult
Externí odkaz:
http://arxiv.org/abs/2406.04973
Autor:
Yang, Mu, Kanda, Naoyuki, Wang, Xiaofei, Chen, Junkun, Wang, Peidong, Xue, Jian, Li, Jinyu, Yoshioka, Takuya
End-to-end speech translation (ST) for conversation recordings involves several under-explored challenges such as speaker diarization (SD) without accurate word time stamps and handling of overlapping speech in a streaming fashion. In this work, we p
Externí odkaz:
http://arxiv.org/abs/2309.08007
Publikováno v:
Shipin gongye ke-ji, Vol 45, Iss 22, Pp 1-8 (2024)
In fruit quality non-destructive testing, information derived from a single data source often falls short in providing a comprehensive representation of the subject under scrutiny, resulting in lower accuracy in detection. Integrating multiple data s
Externí odkaz:
https://doaj.org/article/6bcce24adec34f1b847550ec5619c56f
Publikováno v:
Liang you shipin ke-ji, Vol 32, Iss 5, Pp 67-73 (2024)
To improve the work efficiency and stability of discharger in soybean conditioner, this paper combined the discrete element method to simulate the motion process of soybeans in the discharger, and analyzed the effects of rotor blade number, feeding p
Externí odkaz:
https://doaj.org/article/f52dccd86e244ee8a0ed719156e20d81
Autor:
Huan Ding, Uttam Bhandari, Pengcheng Zhu, Ehsan Bagheri, Saeid Zavari, Yehong Chen, Yang Mu, Yongqiang Wang, Shengmin Guo
Publikováno v:
Journal of Materials Research and Technology, Vol 32, Iss , Pp 2993-3003 (2024)
With standard T6 heat treatments, precipitate-hardened alloys such as Al7075 and Al6061 fabricated using Additive Friction Stir Deposition (AFSD) method restore to noticeablely different peak mechanical properties. Previous research observed similar
Externí odkaz:
https://doaj.org/article/6e74c2c21ad048bf8d186a3733152d93
This study is focused on understanding and quantifying the change in phoneme and prosody information encoded in the Self-Supervised Learning (SSL) model, brought by an accent identification (AID) fine-tuning task. This problem is addressed based on m
Externí odkaz:
http://arxiv.org/abs/2306.06524