检索结果-内蒙古大学图书馆

A reweighting method for speech recognition with imbalanced data of Mandarin and sub-dialects

SERVICE ORIENTED COMPUTING AND APPLICATIONS 2024年第2期18卷 145-152页

作者： Wu, Jiaju Wen, Zhengchang Huang, Haitian Su, Hanjing Liu, Fei Wang, Huan Ding, Yi Wu, Qingyao South China Univ Technol Sch Software Engn Guangzhou Peoples R China Hunan Univ Arts & Sci Changde Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China Pazhou Lab Guangzhou Peoples R China Tencent Wechat Dept Shenzhen Peoples R China Shenzhen Zhenhua Microelect Ltd ZHM Shenzhen Peoples R China Guangdong Inst Sci & Tech Informat Ind Technol Res Ctr Guangzhou Peoples R China

Automatic speech recognition (ASR) is an important technology in many fields like video-sharing services, online education and live broadcast. Most recent ASR methods are based on deep learning technology. A dataset containing training samples of standard Mandarin and its sub-dialects can be used to train a neural network-based ASR model that can recognize standard Mandarin and its sub-dialects. Usually, due to different costs of collecting different sub-dialects, the number of training samples of standard Mandarin in the dataset is much larger than the number of training samples of sub-dialects, resulting in the recognition performance of the model for standard Mandarin being much higher than that of sub-dialects. In this paper, to enhance the recognition performance for sub-dialects, we propose to reweight the recognition loss for different sub-dialects based on their similarity to standard Mandarin. The proposed reweighting method makes the model pay more attention to sub-dialects with larger loss weights, alleviating the problem of poor recognition performance for sub-dialects. Our model was trained and validated on an open-source dataset named KeSpeech, including standard Mandarin and its eight sub-dialects. Experimental results show that the proposed model is better at recognizing most sub-dialects than the baseline and is about 0.5 lower than the baseline in Character Error Rate.

关键词： Automatic speech recognition Imbalanced data Dialect recognition

来源：评论

学校读者我要写书评

暂无评论

Steel Surface Defect Detection Based on Improved YOLOv8 20

Steel Surface Defect Detection Based on Improved YOLOv8

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Zhang, Jichen Zhang, Zhi College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Hubei Wuhan430065 China

ISBN: (纸本)9798350356328

There are some defects on the surface of steel that are difficult to detect, so we propose an improved algorithm based on YOLOv8 for detecting defects that are difficult to be detected. This improvement includes the introduction of an SPD module to minimize the problem of information loss due to downsampling;the addition of a small object detection head combined with EMA attention to further enhance the detection capabilities for small targets;the use of BiFPN to replace the original PANet, applying different weights to different features to strengthen feature fusion. Experiments were conducted on the NEU-DET dataset, and the algorithm improved mAP to 80.2%, an improvement of 3.9% over the baseline model. © 2024 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of Bamboo Resource Survey Application Based on Remote Sensing Images 6

Analysis of Bamboo Resource Survey Application Based on Remo...

引用

6th International Conference on Computer Information Science and Application Technology, CISAT 2023

作者： Liu, Xiaohong Yan, Kai Sun, Maosheng College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650000 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Forestry Southwest Forestry University Kunming650224 China

ISBN: (纸本)9781510668546

Understanding the distribution range of bamboo resources in Yiliang county is important for the ecological services and economic benefits of the county. In this paper, we investigated the distribution of bamboo resources by using 3S (GPS, RS, GIS) technology with remote sensing images and field survey. The survey results show that: the total area of bamboo forest in the county is 65863.72×10-2 km2;the origin of bamboo resources is mainly plantation and natural forest;the types of bamboo forest are pure bamboo forest, tree forest and mixed bamboo forest;the applications are mainly nature reserve bamboo forest, protective bamboo forest, timber bamboo forest and bamboo forest for bamboo shoots;There are 9 kinds of bamboo species, including Jinfo Mountain Fang, Xiaochaoba Fang, Yushan Bamboo, Cixi Bamboo, Mao Bamboo, Bambusa Bamboo, Shui Bamboo, Yongsan Fang and Siban Bamboo;the protection level is Ⅰ, Ⅱ, Ⅲ and Ⅳ respectively. © 2023 SPIE.

关键词： Bamboo

来源：评论

学校读者我要写书评

暂无评论

Homomorphic Encryption based stem cell assay data sharing study

Homomorphic Encryption based stem cell assay data sharing st...

引用

Information Technology,big data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Hengjiang Xiao Zhihong Liang Yuxiang Huang Mingming Qin Fei Xiong Mengxin Liu School of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Key Laboratory of National Forestry and Grassland Administration on Forestry and Ecological Big Data Southwest Forestry University School of Economics and Management Southwest Forestry University Kunming China

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

With the rapid development of the biomedical field, stem cell therapy has received widespread attention as an innovative therapy with great potential. However, privacy protection and secure sharing of stem cell testing data are still major challenges. In this paper, we propose a homomorphic encryption-based data sharing scheme for stem cell testing, which achieves efficient and secure data sharing with data privacy by designing a system architecture covering data acquisition, encryption, transmission, decryption and analysis. Experimental results show that the scheme can not only effectively protect data privacy, but also support efficient data processing with less impact on system performance. The main contributions of this paper include designing and implementing a stem cell detection data sharing system based on homomorphic encryption, proposing a homomorphic encryption algorithm optimised for the high-dimensional characteristics of stem cell data, and experimentally verifying the security and effectiveness of the system. Future research directions include optimising homomorphic encryption algorithms, expanding application scenarios, integrating multiple privacy protection techniques, and optimising system performance.

关键词： data privacy Privacy System performance Medical treatment Systems architecture Stem cells Homomorphic encryption Protection Information technology Testing

来源：评论

学校读者我要写书评

暂无评论

data-Driven Motion-Force Control Scheme for Redundant Manipulators: A Kinematic Perspective

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第8期18卷 5338-5347页

作者： Fan, Jialiang Jin, Long Xie, Zhengtai Li, Shuai Zheng, Yu Lanzhou Univ Sch Informat Sci & Engn Lanzhou 730000 Peoples R China Acad Plateau Sci & Sustainabil Xining 810016 Peoples R China Chinese Acad Sci Chongqing Inst Green & Intelligent Technol Chongqing Key Lab Big Data & Intelligent Comp Chongqing 400714 Peoples R China Lanzhou Univ Dept Comp Sci Lanzhou 730000 Peoples R China Robot X Tencent Shenzhen 518057 Peoples R China

Redundant manipulators play a critical role in industry and academia, which can be controlled from the kinematic or dynamic perspective. The motion-force control of redundant manipulators is a core problem in robot control, especially for the task requiring keeping contact with objectives, such as cutting, polishing, deburring, etc. However, when a manipulator's model structure is unknown, it is challenging to take motion-force control of redundant manipulators. This article proposes a data-driven-based motion-force control scheme, which solves the motion-force control problem from the kinematic perspective. The scheme can take effect and estimate the structure information, i.e., the model parameters involved in the forward kinematics when the structure of the manipulator is incomplete or unknown. A recurrent neural network is devised to find the solution to the scheme. Besides, the theoretical analysis is presented to prove the correctness of the scheme. Simulations and physical experiments running on seven degrees of freedom redundant manipulators illustrate the superb performance and practicability of the scheme intuitively. The key contribution of this article is that, for the first time, a motion-force control scheme aided with data-driven technology is proposed from a kinematic perspective for the redundant manipulators.

关键词： Manipulators Kinematics End effectors Force Jacobian matrices robots Force control data driven kinematic control motion-force control recurrent neural network (RNN) redundant manipulators

来源：评论

学校读者我要写书评

暂无评论

FELSDiff: Image Super-Resolution Based on Diffusion Model Fusing Feature Extraction with Latent Space 20

FELSDiff: Image Super-Resolution Based on Diffusion Model Fu...

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Wu, Cancan Zhang, Zhi Wuhan University of Science and Technology College of Computer Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Hubei Wuhan430065 China

ISBN: (纸本)9798350356328

In addressing issues like an excessive number of network parameters and the loss of fine texture details in image super-resolution reconstruction approaches based on diffusion models, this passage introduces a novel image super-resolution model (FELSDiff). This model relies on the fusion of diffusion models, feature extraction, and latent space. FELSDiff utilizes a Pre-trained CNN for initial super-resolution to extract the primary low-band features and part high-band features of the image. The preliminary super-resolved image is then concatenated as a condition to this model. We introduce a cross-attention mechanism guided by the high-band features of the preliminary super-resolved image to enhance the network's feature extraction capability and obtain more effective features. In the U-Net structure, we incorporate a latent space strategy, enabling the model's training and inference processes to be conducted in the latent space, thereby reducing the number of network parameters. Experimental results on multiple standard datasets indicate that this method outperforms other advanced methods overall. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on patent recommendation method based on graph neural network 26

Research on patent recommendation method based on graph neur...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Enchao Liu, Weidong Liu, Shi Cao, Yan Institute of Scientific and Technical Information of China China College of Computer Science Inner Mongolia University China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350331684

Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation. © 2023 IEEE.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

Interpretable Disease Progression Path for Next Admission Diagnosis Event Prediction in Healthcare data via Hybrid Rule-Transformer Network 11th

Interpretable Disease Progression Path for Next Admission D...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Xu, Fanxin Yu, Hong Su, Zuqiang Zhang, Ping Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing401331 China Sichuan Huhui Software Co. LTD Mianyang China

ISBN: (纸本)9783031927409

Next admission diagnosis event prediction is one of the core tasks based on electronic health records. Existing researches on this task mainly focus on learning accurate disease representations and then fusing these disease representations into deep learning models for learning and prediction. This approach implicitly models the disease progressing path between diseases in the model, while ignoring the explicit disease progression path between diseases that can be established by the data itself. Therefore, it is impossible to accurately and explicitly represent the disease progression path to achieve the purpose of interpreting the disease progression path. For this problem, this paper propose the Hybrid Rule-Transformer Network, it first represent the interpretable disease progression paths as positive region-based decision rules by Pawlak Rough Set, then fuse the original disease embedding and the rule embedding by a dynamic gating fusion strategy, and finally realize the extraction of patient time series modeling information through the Transformer layer. Extensive experiments on two real EHR datasets show that the model this paper established has achieved state-of-the-art in terms of F1-score and Recall, and provides process interpretability of the disease progression paths between visits. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

IF-Font: ideographic description sequence-following font generation 24

IF-Font: ideographic description sequence-following font gen...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xinping Chen Xiao Ke Wenzhong Guo Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou China and Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China

ISBN: (纸本)9798331314385

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Li, Hangying Xu, Changlin Shen, Juhong School of Mathematics and Information Science North Minzu University Ningxia Yinchuan750021 China Key Laboratory of Intelligent Information and Big Data Processing Ningxia Yinchuan750021 China

ISBN: (纸本)9783031927461

To improve the recommendation accuracy of collaborative filtering algorithms, this paper proposes a similarity measurement method based on the concept of normal cloud. First, starting from the characteristic curve of the normal cloud, combining the expected entropy curve and the outer envelope curve of the normal cloud, the paper uses the Bhattacharyya distance to characterize the similarity of probability distributions, and proposes a Bhattacharyya distance-based normal cloud similarity measurement method. Then, numerical simulation experiments are conducted to compare and analyze the performance of the proposed method with existing methods. The experimental results show that the proposed method has a better similarity differentiation capability. Finally, the method is applied to a collaborative filter recommendation system, and experiments are carried out on the MovieLens 100k movie review dataset. The results demonstrate that the proposed method is effective and feasible in collaborative filtering applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：