Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Huajian Fang"'
Publikováno v:
Sensors, Vol 24, Iss 22, p 7241 (2024)
A large number of sensors are required to collect information during the operation of nuclear power plants to ensure their absolutely safe operation. However, because of the unique nature of nuclear reactions, the physical environment of nuclear powe
Externí odkaz:
https://doaj.org/article/73ffb1a8379b4685af5facfeffbd31f3
Publikováno v:
Sustainable Development. 31:540-554
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d862e3defcaeb24d7984037859b25223
https://doi.org/10.1002/sd.2408
https://doi.org/10.1002/sd.2408
Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of reliability.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1785b8d70744ef48e39d838f86355f15
Publikováno v:
Shock and Vibration, Vol 2018 (2018)
Based on Biot’s saturated soil wave theory, using wave function expansion method, theoretical solutions of multiple scattering of plain P1 waves are achieved by rows of cavities as barrier with arbitrarily arranged cavities in saturated soil. Undet
Externí odkaz:
https://doaj.org/article/b5ca7be211624f15a4865baacecf672a
Autor:
Huajian Fang, Timo Gerkmann
Single-channel deep speech enhancement approaches often estimate a single multiplicative mask to extract clean speech without a measure of its accuracy. Instead, in this work, we propose to quantify the uncertainty associated with clean speech estima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ad13857d1b4ce770dea3f058f7aeed0
http://arxiv.org/abs/2212.04831
http://arxiv.org/abs/2212.04831
Speech enhancement in the time-frequency domain is often performed by estimating a multiplicative mask to extract clean speech. However, most neural network-based methods perform point estimation, i.e., their output consists of a single mask. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a858fe153345d6f89ac78ee219c0754
http://arxiv.org/abs/2203.02288
http://arxiv.org/abs/2203.02288
Publikováno v:
ICASSP
Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to noise prese
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90a4b5c9eed0c10ed8094a13173e32ff
Publikováno v:
Journal of Physics: Conference Series. 2253:012021
The text visualization in 3D environment is quite complex due to the characteristics of 3D scene. In this paper we propose to study a group of 3D text information visualization based on parameter study. The primary text information visualization posi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a0d3d80432159133599a85c58d80c52
https://doi.org/10.1088/1742-6596/2253/1/012021
https://doi.org/10.1088/1742-6596/2253/1/012021
Publikováno v:
Shock and Vibration, Vol 2018 (2018)
Based on Biot’s saturated soil wave theory, using wave function expansion method, theoretical solutions of multiple scattering of plain P1waves are achieved by rows of cavities as barrier with arbitrarily arranged cavities in saturated soil. Undete
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db9dcdd6a5ac1fa957d02e7fe432fc8a
https://doi.org/10.1155/2018/4217127
https://doi.org/10.1155/2018/4217127
Publikováno v:
Advanced Sustainable Systems. 6:2100284
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a63ca15a94b69054a28d70b8c0fa3ac
https://doi.org/10.1002/adsu.202100284
https://doi.org/10.1002/adsu.202100284