Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Yuekai Zhang"'
Publikováno v:
iScience, Vol 25, Iss 5, Pp 104183- (2022)
Summary: The designed confocal elliptical core-shell structure can realize the omnidirectional camouflage effect without disturbing temperature and electric potential profiles as the directions of heat flux and electric current change. Based on the a
Externí odkaz:
https://doaj.org/article/c267b4c942614f0e81230eba97cbe020
Publikováno v:
2023 6th International Conference on Communication Engineering and Technology (ICCET).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e8236cda61635defc00c3ca15a65b95
https://doi.org/10.1109/iccet58756.2023.00021
https://doi.org/10.1109/iccet58756.2023.00021
In recent years, deep convolution neural networks (DCNNs) have achieved great prospects in coronary artery vessel segmentation. However, it is difficult to deploy complicated models in clinical scenarios since high-performance approaches have excessi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2350fab7b5e1b1444a32278c7fb3c9f9
http://arxiv.org/abs/2211.00899
http://arxiv.org/abs/2211.00899
Autor:
Xingchen Song, Di Wu, Zhiyong Wu, Binbin Zhang, Yuekai Zhang, Zhendong Peng, Wenpeng Li, Fuping Pan, Changbao Zhu
In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models. The core idea of TrimTail is to apply length penalty (i.e., by trimming trailing frames, see Fig. 1-(b)) directl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73164c219fa8979c4a7801102dde45d5
Publikováno v:
Journal of Biotechnology and Biomedicine.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5df50132e7a08b83b484c52d2fa0d2a
https://doi.org/10.26502/jbb.2642-280049
https://doi.org/10.26502/jbb.2642-280049
Publikováno v:
iScience. 25(5)
The designed confocal elliptical core-shell structure can realize the omnidirectional camouflage effect without disturbing temperature and electric potential profiles as the directions of heat flux and electric current change. Based on the anisotropy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5689630a2cfe19026c5bfa68a9b69811
https://pubmed.ncbi.nlm.nih.gov/35479400
https://pubmed.ncbi.nlm.nih.gov/35479400
Publikováno v:
IEEE Internet of Things Journal. 6:26-37
Orthogonal frequency division multiplexing (OFDM) is widely considered as a promising technique for vehicular communications. In current OFDM-based vehicular communications systems, a portion of tones are dedicated for pilot symbols and transmitted a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c55319c830b6e67c5b35be420475ba58
https://doi.org/10.1109/jiot.2018.2872438
https://doi.org/10.1109/jiot.2018.2872438
Publikováno v:
ICASSP
The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often encounter data limitation problem in building SVS systems because of high
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0538c92a6940a7084e3f1e57baf529e
https://doi.org/10.1109/icassp39728.2021.9414348
https://doi.org/10.1109/icassp39728.2021.9414348
Autor:
Tomoki Hayashi, Wangyou Zhang, Jing Shi, Hirofumi Inaguma, Daniel Garcia-Romero, Chenda Li, Xuankai Chang, Shinji Watanabe, Jiatong Shi, Kun Wei, Yuekai Zhang, Pengcheng Guo, Yosuke Higuchi, Naoyuki Kamo, Florian Boyer
Publikováno v:
ICASSP
In this study, we present recent developments on ESPnet: End-to- End Speech Processing toolkit, which mainly involves a recently proposed architecture called Conformer, Convolution-augmented Transformer. This paper shows the results for a wide range
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa47a67cbbe301048a36e7e10e0659a2
https://doi.org/10.1109/icassp39728.2021.9414858
https://doi.org/10.1109/icassp39728.2021.9414858
Publikováno v:
ICASSP
This paper proposes an extremely lightweight phone-based transducer model with a tiny decoding graph on edge devices. First, a phone synchronous decoding (PSD) algorithm based on blank label skipping is first used to speed up the transducer decoding
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52710d90f4887e8edb9a3d55bc20c277
https://doi.org/10.1109/icassp39728.2021.9413854
https://doi.org/10.1109/icassp39728.2021.9413854