Zobrazeno 1 - 10
of 2 500
pro vyhledávání: '"HOU Feng"'
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 9, Pp 47-52 (2024)
Objective When urban rail transit line adopts the continuous co-phase power supply mode, a fault in the traction network may cause extended power outage due to the complexity and non-backup structure of the traction network. Therefore, it is necessar
Externí odkaz:
https://doaj.org/article/32a0174cf0ea48c0a68800e887b8a8c3
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 6, Pp 296-300 (2024)
Objective As modular co-phase power supply devices are used in Guangzhou Metro Line 18,it is necessary to study the energy-saving operation optimization strategy of the co-phase energy storage power supply system in order to solve the problem of low
Externí odkaz:
https://doaj.org/article/be28f85c7d43464a8588d24c1fbc5267
Publikováno v:
Cailiao gongcheng, Vol 50, Iss 7, Pp 30-39 (2022)
In recent years, photocured ceramics has become one of the rapidly developing additive manufacturing technologies. Bioceramics have a promising future in tissue engineering due to their good cellular compatibility, however, a single bioceramic materi
Externí odkaz:
https://doaj.org/article/b4b29f46a46d444fb9210520eb9b890c
Autor:
Hou, Feng, Yuan, Jin, Yang, Ying, Liu, Yang, Zhang, Yang, Zhong, Cheng, Shi, Zhongchao, Fan, Jianping, Rui, Yong, He, Zhiqiang
Traditional cross-domain tasks, including domain adaptation and domain generalization, rely heavily on training model by source domain data. With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain t
Externí odkaz:
http://arxiv.org/abs/2403.02714
Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates dynamically on the p
Externí odkaz:
http://arxiv.org/abs/2312.08571
In this paper, we propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. While self-training approaches have been extensively developed and evaluated for high-resource languages such as English, their appli
Externí odkaz:
http://arxiv.org/abs/2308.05269
The recently released ChatGPT has demonstrated surprising abilities in natural language understanding and natural language generation. Machine translation relies heavily on the abilities of language understanding and generation. Thus, in this paper,
Externí odkaz:
http://arxiv.org/abs/2304.02182
Publikováno v:
Cybernetics and Information Technologies, Vol 14, Iss 1, Pp 84-100 (2014)
Different students have different learning styles, which are corresponding to their performances and make them behave differently in the learning process. Discovering the learning style of the students can help the development of teaching plans the s
Externí odkaz:
https://doaj.org/article/69fa112eb3a6480b97e8c8d085b0c97e
Autor:
Hou, Feng, Zhang, Yao, Liu, Yang, Yuan, Jin, Zhong, Cheng, Zhang, Yang, Shi, Zhongchao, Fan, Jianping, He, Zhiqiang
Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains. Motivated by
Externí odkaz:
http://arxiv.org/abs/2211.04582
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 4798-4802
We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents some core
Externí odkaz:
http://arxiv.org/abs/2205.06182