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

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

Real Time Face Recognition System using Raspberry Pi4 3

Real Time Face Recognition System using Raspberry Pi4

引用

3rd International Conference on Advanced Electrical Engineering, ICAEE 2024

作者： Boukerche, Alaa Eddine Chelali, Fatma Zohra University of Science and Technology Houari Boumediene Usthb Faculty of Electrical Engineering Telecommunications Department Algeria University of Science and Technology Houari Boumediene Usthb Speech Communication and Signal Processing Laboratory Faculty of Electrical Engineering Algeria

ISBN: (数字)9798350349351

ISBN: (纸本)9798350349351

Modern technologies like computer vision (CV), Artificial Intelligence (AI), the internet of things (IoT), and (AIoT) Artificial Intelligence of Things have advanced in many fields, particularly surveillance systems, which need to process faces in real time to guarantee security. This paper proposed a comparative analysis for a real time face recognition system from video sequences with two architectures including traditional application using a personal computer and a Raspberry Pi, respectively. Our study offers an implementation for a real-time face recognition system employing Viola-Jones algorithm and Deep neural networks techniques such as Convolutional Neural Networks (CNN) for face detection and face recognition. Our face recognition system seeks to replace the conventional approach of keeping track of attendance by implementing a Raspberry Pi-based attendance monitoring system that can be utilized by all institutions and organizations. Significant progress has been made thanks to the use of CNN models which has allowed an accuracy rate of 94%. © 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

Coverage Probability of EH-enabled LoRa networks - A Deep Learning Approach

EAI Endorsed Transactions on Industrial Networks and Intelli...

引用

EAI Endorsed Transactions on Industrial Networks and Intelligent Systems 2025年第2期12卷 1-11页

作者： Nguyen, Thi-Tuyet-Hai Hung, Tran Cong Son, Nguyen Hong Hanh, Tan Duy, Tran Trung Tu, Lam-Thanh Faculty of Information Technology Posts and Telecommunications Institute of Technology Viet Nam School of Computer Science & Engineering Saigon International University Ho Chi Minh City Viet Nam Faculty of Telecommunications Posts and Telecommunications Institute of Technology Viet Nam Communication and Signal Processing Research Group Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam

The performance of energy harvesting (EH)-enabled long-range (LoRa) networks is analyzed in this work. Specifically, we employ deep learning (DL) to estimate the coverage probability (Pcov) of the considered networks. Our study incorporates a general fading distribution, specifically the Nakagami-m distribution, and utilizes tools from stochastic geometry (SG) to model the spatial distributions of all nodes and end-devices (EDs) with EH capability. The DL approach is employed to overcome the limitations of model-based methods that can only evaluate the Pcov under simplified network conditions. Therefore, we propose a deep neural network (DNN) that estimates the Pcov with high accuracy compared to the ground truth values. Additionally, we demonstrate that DL significantly outperforms the Monte Carlo simulation approach in terms of resource consumption, including time and memory. © (2025), (European Alliance for Innovation). All rights reserved.

关键词： Coverage probability deep learning energy harvesting long range power beacon

来源：评论

学校读者我要写书评

暂无评论

Resource-efficient neural networks for embedded systems

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2506-2556页

作者： Wolfgang Roth Günther Schindler Bernhard Klein Robert Peharz Sebastian Tschiatschek Holger Fröning Franz Pernkopf Zoubin Ghahramani Graz University of Technology Austria Laboratory of Signal Processing and Speech Communication Heidelberg University Germany Institute of Computer Engineering Graz University of Technology Austria Institute of Theoretical Computer Science University of Vienna Austria Faculty of Computer Science University of Cambridge UK

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on resource-efficient inference based on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briey discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark data sets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and prediction quality.

关键词： resource-efficient machine learning inference deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Packet loss concealment-based estimation of polynomial interpolation for improving speech quality in VoIP

引用

International Journal of Intelligent Systems Technologies and Applications 2020年第5期19卷 486-499页

作者： Bakri, Adil Amrouche, Abderrahmane Speech Communication and Signal Processing Laboratory LCPTS Faculty of Electronics and Computer Science USTHB B.P. 32 Bab-Ezzouar Algiers16111 Algeria

The main objective of packet loss concealment (PLC) techniques is to improve the speech quality in voice over IP (VoIP). These techniques generate a synthetic speech signal to cover the missing data or the lost packets in a received bit stream. This paper is concerned with performing a new PLC technique using the estimation of polynomial interpolation (EPI) method, which is designed to seek the approximate function as a polynomial. This function can be used to predict the lost packet from previous packets. A two state Markov model, particularly, is used to represent the lost packets. The used test vectors, in the proposed PLC evaluation, are the TIMIT database. Thus, the proposed PLC algorithm, which is provided better speech quality, is evaluated by PESQ and SNR and compared to two techniques;the hidden Markov model (HMM)-based PLC algorithm and the deep neural network (DNN)-based PLC. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MCFTNet: Multimodal Cross-Layer Fusion Transformer Network for Hyperspectral and LiDAR Data Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12803-12818页

作者： Huang, Wei Wu, Tianren Zhang, Xueyu Li, Liangliang Lv, Ming Jia, Zhenhong Zhao, Xiaobin Ma, Hongbing Vivone, Gemine Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi830017 China Guangxi University School of Computer and Electronic Information Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Tsinghua University Department of Electronic Engineering Beijing100084 China National Research Council Tito85050 Italy National Biodiversity Future Center NBFC Palermo90133 Italy

Remote sensing image classification is a popular yet challenging field. Many researchers have combined convolutional neural networks (CNNs) and Transformers for hyperspectral imaging (HSI) classification tasks. However, in traditional Transformers, shallow-level information does not propagate well to deeper layers, which can lead to spatial variations and overfitting. Moreover, traditional Transformer models use an external classification token (CLS token) that is randomly initialized and often struggles to generalize effectively. In this article, we combine the strengths of HSI and light detection and ranging (LiDAR) data, using LiDAR as an external CLS token, which significantly enhances classification accuracy and reliability. We propose a new multimodal cross-layer fusion transformer network (MCFTNet), integrating CNNs with the latest Transformer networks. It includes a CNN for extracting spatial features and a hybrid cross-patch attention mechanism for land cover classification, leveraging LiDAR data to generate CLS and HSI patch tokens. More importantly, to reduce the loss of valuable information during the layer-by-layer propagation, we designed cross-layer skip connections. Through adaptive learning, these cross-layer fusions help address the gradient vanishing problem in deep networks while preserving early-layer features. This enables the model to better integrate information from different layers, enhancing both its stability and performance. We carried out in-depth experiments on commonly used benchmark datasets, specifically, the University of Houston dataset, the Trento dataset, and the University of Southern Mississippi Gulf Park dataset. We compared the results of the proposed MCFTNet model with those obtained from state-of-the-art Transformer models, classical CNNs, and traditional classifiers. As a result, the MCFTNet model outshones them all in terms of performance. © 2008-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Watermarking Technique Using Convolutional Autoencoder

Image Watermarking Technique Using Convolutional Autoencoder

引用

Advances in electronics, Control and communication Systems (ICAECCS), International Conference on

作者： Elchaimae Rebahi Mustapha Hemis Bachir Boudraa Speech Communication and Signal Processing Laboratory Faculty of Electrical Engineering University of science and technology Houari BOUMEDIENE (USTHB) BP 32 El Alia Algiers Algeria

Due to the rapid growth in communication networks and data sharing, protecting copyrights has become increasingly important. Digital watermarking is seen as a promising solution to resolve this issue. A new blind digital watermarking based on deep convolutional auto-encoders is presented in this paper. The system facilitates the embedding and extraction of a watermark in an image for its protection. The proposed architecture comprises four modules: an “encoder” that compresses the original image and watermark, an “embedder” that combines the two, a “decoder” that upsamples the combined result to reconstruct the watermarked image, and an “extractor” for watermark retrieval. The experimental results indicate that the watermarked images maintain their visual quality after insertion, and the extracted watermark remains robust against various various attacks such as filtering, rotation, and noise.

关键词： Visualization Image resolution Image coding Filtering Watermarking Control systems Robustness

来源：评论

学校读者我要写书评

暂无评论

GMM Evaluation for Speaker Identification

GMM Evaluation for Speaker Identification

引用

2022 International Conference of Advanced Technology in Electronic and Electrical Engineering, ICATEEE 2022

作者： Bounazou, Hadjer Asbai, Nassim Zitouni, Sihem Mohamed El Bachir El Ibrahimi University ETA Laboratory Department of Electronic Bordj Bou Arreridj34030 Algeria USTHB Speech Com. Signal Proc Lab Faculty of Electronics and Computer Sciences Bab Ezzouar16 111 Algeria Mohamed El Bachir El Ibrahimi University Faculty of Mathematics and Computer Science Department of Computer Science Bordj Bou Arreridj34030 Algeria

ISBN: (纸本)9798350346749

This work present the results obtained with an automatic speaker identification system, which we have developed and which is based on the GMM speaker modeling method, the identification task is assigned to the GMM-UBM. Several experiments of automatic speaker identification carried out in quiet and noisy environments, on TIMIT database is studied. We experimentally show that increasing the number of adaptation coefficients beyond 10 does not bring a significant improvement of the identification rate in quiet environment. and show degradation on performance when the environment where our identification system is operational becomes noisy. © 2022 IEEE.

关键词： Loudspeakers

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：