Zobrazeno 1 - 10
of 46
pro vyhledávání: '"JIA Hairong"'
Publikováno v:
Taiyuan Ligong Daxue xuebao, Vol 55, Iss 4, Pp 743-750 (2024)
Purposes In order to predict the traffic of 5G base stations more accurately and analyze the tidal phenomenon, a traffic prediction method of GAN model with differential algorithm is proposed to improve the gray wolf optimized LSTM. And the modified
Externí odkaz:
https://doaj.org/article/e9e7bb0e0f784e29ab42f57c756bdd2d
Publikováno v:
Taiyuan Ligong Daxue xuebao, Vol 55, Iss 4, Pp 720-726 (2024)
Purposes In order to solve the computational cost problem of complex model in time and hardware, and improve the performance of speech enhancement algorithm, a speech enhancement algorithm using multi-task adaptive knowledge distillation is proposed.
Externí odkaz:
https://doaj.org/article/da0f1c7bb3c14e04acd4ddc4c1b6b656
Autor:
Jia, Hairong1 (AUTHOR), Su, Wenhao1 (AUTHOR), Zhang, Jiaqi1 (AUTHOR), Wei, Zhaoyang1 (AUTHOR), Tsikwa, Pepertual1 (AUTHOR), Wang, Yanru1 (AUTHOR) WangYR8051@outlook.com
Publikováno v:
PLoS ONE. 9/26/2024, Vol. 19 Issue 9, p1-8. 8p.
Publikováno v:
In Applied Acoustics 1 January 2021 171
Publikováno v:
Computer Journal; Jun2024, Vol. 67 Issue 6, p2246-2256, 11p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2009 International Forum on Computer Science-Technology and Applications.
A speech enhancement method based on signal subspace and hearing masking effect is proposed. This method has following steps. Firstly, by subspace filter the noisy speech is enhanced. Then by Johnston hearing masking model the noise hearing masking t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::00caf46b5e2914016142678daf591c3d
https://doi.org/10.1109/ifcsta.2009.241
https://doi.org/10.1109/ifcsta.2009.241
Publikováno v:
Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).
A new blind equalization algorithm based on LMS-Newton gradient is proposed. In order to decline complexity of algorithm and obtain faster convergence speed, a new cost function according to the principle of Euclidean distance is designed. The effect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6450d6165b2babd63377d0ddf7c6498c
https://doi.org/10.1109/wcica.2004.1340584
https://doi.org/10.1109/wcica.2004.1340584
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2009 International Forum on Computer Science-Technology & Applications; 2009, p15-18, 4p