检索结果-内蒙古大学图书馆

5th International Conference on Electrical Engineering and Control Applications, ICEECA 2022

作者： Bakri, Adil Mahdjane, Karima Amrouche, Abderrahmane Krobba, Ahmed Scientific Research and Technical Center for the Development of Arabic Language CRSTDLA Algiers Algeria Speech Communication and Signal Processing Laboratory Faculty of Electronics and Computer Science USTHB Algiers Algeria

ISBN: (纸本)9789819747757

In this paper, a Packet Loss Concealment (PLC) algorithm is proposed for G723.1 CELP-type speech coders in order to improve the quality of decoded speech in VoIP under burst packet loss. The original PLC method implemented in this codec is based on the generation of excitations. The generated excitations are used as input to the LP synthesis filter based on past LP coefficients. In an easier way, it relies on the last frame, which is well received to generate a new frame that replaces the lost frame. The proposed PLC is designed as a PLC algorithm for G.723.1. The proposed method performance is compared with the PLC algorithm employed in G.723.1, through the Perceptual Evaluation of speech Quality (PESQ). The experiments have shown that the proposed PLC algorithm provides significant enhancement of the speech quality than the PLC of G.723.1, especially in the presence of burst packet loss and voice onset conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning and Deep Learning for Static and Dynamic Hand Gesture Recognition

Using Machine Learning and Deep Learning for Static and Dyna...

引用

2024 International Conference on Advances in Electrical and communication Technologies, ICAECOT 2024

作者： Sebbah, Raouf Chelali, Fatma Zohra University of Sciences and Technology Houari Boumediene Speech communication and signal processing laboratory Faculty of Electrical Engineering Box n°32 El Alia Algiers16111 Algeria

ISBN: (纸本)9798350353754

Human-computer interaction aims at facilitating interaction between the hearing-impaired people and the hearing community. It focuses more on the gestural interfaces that require hand movements, which need complex algorithms to be identified. The objective of this paper is to recognize and identify static and dynamic hand gestures by using deep neural network technique, which is based on ResNet18 and a machine learning technique that is based on LGBPHS descriptor. In addition, one-against-all Support Vector Machine and the k-nearest neighbor are applied to classify the feature hand gestures obtained by these two different systems. The findings showed that ResNet18 led to higher hand recognition accuracy than LGBPHS descriptor. Regarding static hand gestures, a result of 99.16% was achieved using ResNet18 on Jochen Triesch's dataset, and a recognition rate of 90.66% was obtained on Arabic sign language dataset. For dynamic hand gestures, a recognition rate of 91.66% was found on Sebastien Marcel. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Bimodal fusion of visual and speech data for audiovisual speaker recognition in noisy environment

引用

International Journal of Information Technology (Singapore) 2023年第6期15卷 3135-3145页

作者： Chelali, Fatma Zohra Speech communication and signal processing laboratory Faculty of Electronics engineering Telecommunications Department University of Science and Technology Houari Boumedienne (USTHB) El Alia Box n:32 Algiers 16111 Algeria

In human communications, the understanding of visual/acoustic signals as well as speaker recognition in noisy environment is an important task, in our daily life. In this work, we focus on the problem of audiovisual data fusion, in order to combine the acoustic and visual modalities in such a way that the recognition system becomes quite robust to the environmental noises. The approach adopted to achieve this work is conducted in two steps: The 1st step consists in the extraction of low-level features such as Linear Predictive coding LPC and the Mel cepstral coefficients (MFCC) for the acoustic information, whereas the Zernike moments (ZM) with the Histogram of oriented gradient (HOG) are used for the visual information. In the 2nd step, we carry out a fusion of the different features: acoustic and visual descriptors, to improve the efficiency of each modality. Furthermore, a comparison with late integration using a score-based fusion is carried out too. We proposed an artificial neural network (MLP) as a classifier for achieving this task. Results show the superiority of the visual modality compared to the acoustic one, in noisy environment, and the high performances of the fusion technique. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Audio visual speaker identification Early integration fusion, intermediate integration fusion late integration fusion HOG LPC MFCC NN Zernike moments

来源：评论

学校读者我要写书评

暂无评论

Arduino Voice Control for Arabic speech Recognition using Smartphone 6

Arduino Voice Control for Arabic Speech Recognition using Sm...

引用

6th International Hybrid Conference on Informatics and Applied Mathematics, IAM 2023

作者： Bakri, Adil Lounnas, Khaled Lichouri, Mohamed Scientific and Technical Research Centre on Arid Regions CRSTRA Biskra Algeria Scientific Research and Technical Center for the Development of Arabic Language CRSTDLA Algiers Algeria Speech Communication and Signal Processing Laboratory LCPTS Faculty of Electronics and Computer Science USTHB Algiers Algeria

Engaging with our surroundings through voice control has emerged as an increasingly intriguing aspect. This technology is gaining prevalence in our daily lives, whether applied in smart homes, mobile phones, or the control of comfort features in vehicles. The pertinent inquiry is whether voice control will find its place in the production industry, as its reliability remains a critical concern. This project showcases an alternative approach to voice processing by integrating Arabic speech recognition in MIT App Inventor for voice command control. In this setup, voice signals undergo processing, enabling the operation of a LED light circuit through Bluetooth technology. The voice command is given in Arabic through the smartphone device having Bluetooth and the command is transferred and converted to string by the BT Voice Control for Arduino and is transferred to the Bluetooth Module connected to the Arduino board for the control of the LED light circuit. The voice command Arabic is given through a Smartphone device. © 2023 Copyright for this paper by its authors.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition Based on LPQ and MRELBP Descriptors

Hand Gesture Recognition Based on LPQ and MRELBP Descriptors

引用

2021 International Conference on Artificial Intelligence for Cyber Security Systems and Privacy, AI-CSP 2021

作者： Hamou, Assia Ould Chelali, Fatma Zohra Speech Communication and Signal Processing Laboratory Faculty of Electronic and Computer Sciences Algiers16111 Algeria

ISBN: (纸本)9781665467148

Gesture is an important communication tool, either for human-to-human communication, particularly to the estimated 70 million hearing-impaired people across the globe or for Human-Machine communication such as the human-machine interaction (HMI). In this paper, we propose an implementation of a static and dynamic gesture recognition system using three databases (American Sign Language ASL, Arabic Sign Language ArSL, and dynamic Clic) in an uniform background. The system is based on the Local Phase Quantization (LPQ) and the Median Robust Extended Local Binary Pattern (MRELBP) where the recognition task is applied using the Radial Basis Function Neural Network (RBF-NN) and the Support Vector Machine (SVM) classification techniques. Satisfactory results were obtained where the best recognition rate reached 97,5 % for American Language using LPQ descriptor. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Sparsity-aware Subband Adaptive Filtering in Impulsive Interferences 7

Sparsity-aware Subband Adaptive Filtering in Impulsive Inter...

引用

7th IEEE International Conference on Electronic Information and communication Technology, ICEICT 2024

作者： Gong, Zhikai Li, Yingsong Pang, Baohe Li, Xueyan Xiao, Wudang Li, Liping Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing China Innopolis University Faculty of Computer and Engineering Sciences Russia

ISBN: (纸本)9798350384437

In this paper, we propose two new subband adaptive filtering (SAF) algorithms based on the cost function of the logistic distance metric cost function and use the proportionate proximal gradient algorithm to exploit the sparsity of the system fully. Compared with prior works, the proposed algorithms can handle many different situations better. Through computer simulations, we prove that the algorithm performs excellently in sparse systems disturbed by impulse noises. The algorithm can be used in areas like system identifications. © 2024 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Near-field Source DOA Estimation Algorithm Based on De-impact Function under Impulse Noise 7

Near-field Source DOA Estimation Algorithm Based on De-impac...

引用

7th IEEE International Conference on Electronic Information and communication Technology, ICEICT 2024

作者： Xu, Xingchao Pang, Baohe Li, Yingsong Li, Liping Zou, Dingcheng Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Innopolis Russia

ISBN: (纸本)9798350384437

In addressing the issue of localizing near-field source signals in the presence of impulse noise, this manuscript introduces a novel de-impact function designed for preprocessing received signals to alleviate the interference caused by impulse noise. Simulation experiments verify the effectiveness of the proposed de-impact function in effectively suppressing impulse noise. Furthermore, to augment estimation precision, a novel algorithm for near-field source localization is proposed. Building upon the framework of correlation entropy theory, a new correntropy covariance matrix is formulated to replace the original signal covariance matrix for signal processing. Through a succession of low-bias approximations between near-field and far-field scenarios, the algorithm converts the original 2-D search into 1-D operations. Additionally, the conventional spectral peak search is replaced by polynomial solving to further mitigate the computational complexity of the algorithm. © 2024 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

High Degree of Freedom Low Coupling Sparse MIMO Array 7

High Degree of Freedom Low Coupling Sparse MIMO Array

引用

7th IEEE International Conference on Electronic Information and communication Technology, ICEICT 2024

作者： Yao, Yichang Pang, Baohe Li, Yingsong Yu, Canping Xiao, Wudang Li, Liping Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Innopolis Russia

ISBN: (纸本)9798350384437

To achieve high precision direction-of-arrival estimation of MIMO arrays in highly coupled environments, based on the difference and cooperative array principles, the uniform array fitted with 5 base layer array and the uniform array fitted with 6 base layer array were used as transmitting arrays, and with the addition of 1 base layer layer sparse array as receiving array, two sparse multi-in multiple-out arrays were designed for single-base radar, which have the characteristics of low coupling of transmitting array and high freedom of receiving array. © 2024 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Low Coupling Sparse Array Based on Uniform Linear Array Fitting Method 7

Low Coupling Sparse Array Based on Uniform Linear Array Fitt...

引用

7th IEEE International Conference on Electronic Information and communication Technology, ICEICT 2024

作者： Yao, Yichang Li, Yingsong Li, Liping Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Innopolis Russia

ISBN: (纸本)9798350384437

In order to solve the problem that traditional sparse arrays only emphasize high degrees of freedom and ignore low coupling, uniform array fitting method can design arrays with low coupling. However, the existing array coupling based on uniform array fitting method still has room for decline, and the value of weight function is not the minimum, so the performance of array DOA estimation needs to be further optimized. Therefore, based on the uniform matrix fitting method, a uniform matrix fitting 6-base-layer array is designed. By extending the spacing of each subarray of the uniform subarray in the base layer, the number of small array element spacing pairs in the differential cooperative array is reduced, and the coupling between the elements of the whole sparse array is reduced as a whole. The performance of DOA estimation of the designed array is simulated and analyzed by using spatial smoothing multiple signal classification algorithm. © 2024 IEEE.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning and Deep Learning for Static and Dynamic Hand Gesture Recognition

Using Machine Learning and Deep Learning for Static and Dyna...

引用

Advances in Electrical and communication Technologies (ICAECOT), International Conference on

作者： Raouf Sebbah Fatma Zohra Chelali Speech communication and signal processing laboratory Faculty of Electrical Engineering University of Sciences and Technology Houari Boumediene Box n○:32 El Alia Algiers Algeria

ISBN: (数字)9798350353754

ISBN: (纸本)9798350353761

Human-computer interaction aims at facilitating interaction between the hearing-impaired people and the hearing community. It focuses more on the gestural interfaces that require hand movements, which need complex algorithms to be identified. The objective of this paper is to recognize and identify static and dynamic hand gestures by using deep neural network technique, which is based on ResNet18 and a machine learning technique that is based on LGBPHS descriptor. In addition, one-against-all Support Vector Machine and the k-nearest neighbor are applied to classify the feature hand gestures obtained by these two different systems. The findings showed that ResNet18 led to higher hand recognition accuracy than LGBPHS descriptor. Regarding static hand gestures, a result of 99.16% was achieved using ResNet18 on Jochen Triesch’s dataset, and a recognition rate of 90.66% was obtained on Arabic sign language dataset. For dynamic hand gestures, a recognition rate of 91.66% was found on Sebastien Marcel.

关键词： Hands Support vector machines Human computer interaction Sign language Accuracy Machine learning algorithms Artificial neural networks Nearest neighbor methods Vectors Object recognition

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：