Zobrazeno 1 - 10
of 129
pro vyhledávání: '"Zhu Weibin"'
Publikováno v:
Metrology and Measurement Systems, Vol 27, Iss 1, Pp 51-64 (2020)
The contradiction between the restriction of grating manufacturing technology and high-resolution measurement requirements has been the focus of attention. The precision requirement of angle calculation during the digital subdivision processing of a
Externí odkaz:
https://doaj.org/article/81933d636e424485a1b273663f7bd5e1
Autor:
Srivannavit, Onnop, Joshi, Rakesh, Zhu, Weibin, Gong, Bin, Sealfon, Stuart C., Borca-Tasciuc, Theodorian, Gaitas, Angelo
This study presents a novel thermocouple instrument designed for precise temperature monitoring within biological tissues and cells, addressing a significant gap in biological research. Constructed on a Silicon-On-Insulator (SOI) substrate, the instr
Externí odkaz:
http://arxiv.org/abs/2403.16796
Publikováno v:
E3S Web of Conferences, Vol 261, p 02009 (2021)
Civil aircraft is the most complicated production of the world and during the manufacture various kinds of manufacture nonconformities occur at times. Superfluous hole is one of the most typical nonconformity types. When coping with this kind of prob
Externí odkaz:
https://doaj.org/article/71a2f08a91f741ebae048c4c051c7755
In recent years, self-supervised learning (SSL) has achieved tremendous success in various speech tasks due to its power to extract representations from massive unlabeled data. However, compared with tasks such as speech recognition (ASR), the improv
Externí odkaz:
http://arxiv.org/abs/2211.06041
Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is changed, wh
Externí odkaz:
http://arxiv.org/abs/2204.00226
The harmonic structure of speech is resistant to noise, but the harmonics may still be partially masked by noise. Therefore, we previously proposed a harmonic gated compensation network (HGCN) to predict the full harmonic locations based on the unmas
Externí odkaz:
http://arxiv.org/abs/2202.12643
Mask processing in the time-frequency (T-F) domain through the neural network has been one of the mainstreams for single-channel speech enhancement. However, it is hard for most models to handle the situation when harmonics are partially masked by no
Externí odkaz:
http://arxiv.org/abs/2201.12755
Publikováno v:
In Journal of Power Sources 30 September 2024 615
Autor:
Wang, Tianrui, Zhu, Weibin
Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although the existing
Externí odkaz:
http://arxiv.org/abs/2108.11877