Zobrazeno 1 - 10
of 530
pro vyhledávání: '"joint training"'
Autor:
CAO Taisheng, ZHAI Chenqi
Publikováno v:
Jiaoshi jiaoyu xuebao, Vol 11, Iss 4, Pp 19-29 (2024)
In July 2023, China issued the Opinions of the Ministry of Education on Implementing the National Excellent Primary and Secondary School Teacher Training Plan, which requires the implementation of the "National Excellent Primary and Secondary School
Externí odkaz:
https://doaj.org/article/f6b30521fbeb4b0089dd02f68f13461f
Publikováno v:
Zhihui kongzhi yu fangzhen, Vol 46, Iss 3, Pp 43-48 (2024)
The intending goal of modeling and simulation is to create a unified Live-Virtual-Constructive (LVC) integration architecture, support rapid integration model and carry out simulation for joint flight training, tactical coordination, operational plan
Externí odkaz:
https://doaj.org/article/3644e9ba588d4a3a9b8d0d3acac155ea
Research and Manufacturing of Wrist Joint Rehabilitation Robots Based on the 3-UU Parallel Mechanism
Publikováno v:
Jixie chuandong, Vol 48, Pp 162-171 (2024)
Based on the 3-UU parallel mechanism, a prototype robot for wrist joint rehabilitation is developed to assist stroke patients in wrist joint rehabilitation training. Based on the constraint relation and geometric characteristics of the 3-UU mechanism
Externí odkaz:
https://doaj.org/article/099efe3ce7344388b4546eb7e0e26d89
Publikováno v:
IEEE Photonics Journal, Vol 16, Iss 6, Pp 1-12 (2024)
Compared with conventional imaging methods, Fourier single-pixel imaging (FSPI) has efficient noise immunity, wide spectral coverage, non-local imaging ability and long imaging range. Leveraging FSPI for object detection holds promising applications.
Externí odkaz:
https://doaj.org/article/6d7695b1c34347c9981995cc676d450c
Publikováno v:
IEEE Access, Vol 12, Pp 111673-111682 (2024)
Speech data gathered from real-world environments typically contain noise, a significant element that undermines the performance of deep neural network-based speaker verification (SV) systems. To mitigate performance degradation due to noise and deve
Externí odkaz:
https://doaj.org/article/72984ed1187c4c739336eeb46abf22bf
Publikováno v:
IEEE Access, Vol 12, Pp 72566-72577 (2024)
As the problem of information overload becomes more severe, it has become increasingly difficult for users to browse news that they are interested in. News recommendation is an effective method to alleviate this problem. In news recommendation, accur
Externí odkaz:
https://doaj.org/article/62c0054518494ca795a315f5467e6626
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-10 (2023)
Abstract Target speaker separation aims to separate the speech components of the target speaker from mixed speech and remove extraneous components such as noise. In recent years, deep learning-based speech separation methods have made significant bre
Externí odkaz:
https://doaj.org/article/4369696e6e854b868e5fda19c154156c
Publikováno v:
Mathematics, Vol 12, Iss 17, p 2659 (2024)
Graph neural networks (GNNs) have been highly successful in graph representation learning. The goal of GNNs is to enrich node representations by aggregating information from neighboring nodes. Much work has attempted to improve the quality of aggrega
Externí odkaz:
https://doaj.org/article/5adb5fa3064943ed9ca198dbfd76e31e
Publikováno v:
Entropy, Vol 26, Iss 5, p 371 (2024)
The integration of graph embedding technology and collaborative filtering algorithms has shown promise in enhancing the performance of recommendation systems. However, existing integrated recommendation algorithms often suffer from feature bias and l
Externí odkaz:
https://doaj.org/article/6550f1ef2d9b430fb914aee09561be48
Autor:
Geon Woo Lee, Hong Kook Kim
Publikováno v:
Sensors, Vol 24, Iss 8, p 2573 (2024)
This paper addresses a joint training approach applied to a pipeline comprising speech enhancement (SE) and automatic speech recognition (ASR) models, where an acoustic tokenizer is included in the pipeline to leverage the linguistic information from
Externí odkaz:
https://doaj.org/article/4807ebf3ec1b4ff4873c10b7d8e5532b