检索结果-内蒙古大学图书馆

Deep neural networks for speech enhancement and speech recognition: A systematic review

Ain Shams engineering Journal 2025年第7期16卷

作者： Natarajan, Sureshkumar Rahman Al-Haddad, Syed Abdul Ahmad, Faisul Arif Kamil, Raja Hassan, Mohd Khair Azrad, Syaril Macleans, June Francis Abdulhussain, Sadiq H. Mahmmod, Basheera M. Saparkhojayev, Nurbek Dauitbayeva, Aigul Department of Computer and Communication Systems Engineering Universiti Putra Malaysia Selangor Serdang43400 Malaysia Department of Electrical and Electronic Engineering Universiti Putra Malaysia Selangor Serdang43400 Malaysia Department of Aerospace Engineering Universiti Putra Malaysia Selangor Serdang43400 Malaysia Malaysia Department of Computer Engineering University of Baghdad Iraq Rudny Industrial University Kazakhstan Department of Computer Science Korkyt Ata Kyzylorda State University Kazakhstan

The field of speech signal processing has undergone significant transformation through extensive research. There is growing interest in Speech Enhancement (SE) and Automatic Speech Recognition (ASR), with SE serving as a crucial preliminary step to enhance ASR performance. This paper addresses key challenges, particularly the need to maintain speech quality and improve intelligibility in ASR systems. Recently, deep learning techniques have emerged as powerful tools for tackling these challenges. This systematic review examines speech enhancement and recognition techniques, emphasizing denoising, acoustic modeling, and beamforming. Various deep learning architectures, such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Hybrid Neural Networks, are reviewed to highlight their roles in enhancement and recognition. The review specifically details their usage, the features utilized in each study, the databases employed, performance, and limitations, all presented in a structured tabular format. This approach provides valuable insights into the strengths and weaknesses of each method, guiding future advancements in the field. In particular, it emphasizes that LSTM-RNN models excel in temporal signal processing, while hybrid models demonstrate superior performance in optimizing task outcomes. The paper conducts a comprehensive statistical analysis of 187 research papers that exclusively utilize deep neural networks to address the challenges of speech enhancement and recognition, presenting the latest advances in the field. The review examines publications from 2012 to 2024, shedding light on research trends and patterns, while the proposed solutions aim to bridge gaps for researchers in this evolving domain. © 2025 The Author(s)

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

An integrated decision support framework for exploring the barriers and potential application scenarios in metaverse hospitality

引用

Journal of industrial Information Integration 2025年 45卷

作者： Wu, Qun Tan, Weiqi Zhou, Ligang Deveci, Muhammet Pamucar, Dragan Pedrycz, Witold School of Mathematical Sciences Anhui University Hefei230601 China Anhui University Center for Applied Mathematics Anhui University Hefei Anhui230601 China Department of Industrial Engineering Turkish Naval Academy National Defence University Istanbul34942 Tuzla Turkey Royal School of Mines Imperial College London LondonSW7 2AZ United Kingdom Department of Information Technologies Western Caspian University Baku1001 Azerbaijan Faculty of Organizational Sciences University of Belgrade Belgrade11000 Serbia Department of Electrical and Computer Engineering University of Alberta Edmonton ABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland

The global hospitality industry is undergoing a profound transformation, primarily driven by the internet era within the context of Industry 4.0 and the continuous evolution of the metaverse. The metaverse offers limitless possibilities for creating immersive and personalized accommodation experiences by closely integrating the virtual with the real world. It also provides a new perspective and mindset for guiding the hospitality industry to rethink and redesign service models and business processes. Although the metaverse application in the hospitality industry has already made significant progress, this process still faces numerous barriers, and the specific application scenarios of the metaverse hospitality industry (MHI) remain unclear. This study aims to develop an integrated decision support framework for exploring the barriers and potential application scenarios in metaverse hospitality. First, the interval type-2 fuzzy sets (IT2FSs) is introduced to quantify the complex and uncertain information in the decision-making procedure. Second, the IT2F-BWM with the IT2F weighted averaging (IT2FWA) operator is proposed to calculate the barriers’ weights considering the group opinions. Third, the IT2FWA operator and IT2F-ExpTODIM method are incorporated to prioritize the potential application scenarios in MHI. Finally, a case study on the prioritization of barriers and application scenarios in MHI is utilized to test the effectiveness and practicality of the presented framework. Results show that the technology barrier (0.5217) and the interaction technology (0.2483) have the highest levels among the main and sub-main barrier hierarchies, respectively. The findings of this article may enrich the theories of uncertain decision-making methods and provide instructive suggestions for the operation and management of metaverse hospitality practice. © 2025 Elsevier Inc.

关键词： IT2F-BWM IT2F-ExpTODIM Metaverse hospitality Multi-criteria decision-making

来源：评论

学校读者我要写书评

暂无评论

Design of a WSN software stack Synthesis Evaluation Module

Design of a WSN software stack Synthesis Evaluation Module

引用

2013 IEEE 24th International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC Workshops 2013

作者： Antonopoulos, Ch.P. Kerasiotis, F. Koulamas, C. Papadopoulos, G. Koubias, S. Department of Electrical and Computer Engineering University of Patras Greece Industrial Systems Institute Patras Greece

ISBN: (纸本)9781479901227

Although Wireless Sensor Networks (WSNs) comprise one of the most rapidly evolving networking areas, in order to achieve significant widespread use, it is essential to provide tools enabling WSN users (especially the non-expert ones) to design, develop and deploy efficient WSNs with respect to specific requirements. Despite the importance of such objectives a significant lack is identified in the current state-of-the-art development environments, targeting almost exclusively towards expert WSN users and thus requiring significant programming familiarity and WSN in-depth knowledge. This paper aims to present an approach addressing this shortcoming by proposing an efficient Synthesis Evaluation Module (SEM). Through identification and utilization of each software layer's critical characteristics and providing, that appropriate architectural characteristics concerning the system's property predictability are adopted, accurate synthesis indications can be issued to the user. In this way, the user, and particularly the non-expert WSN user, can select the optimal SW synthesis or/and HW platform with respect to the application requirements, thus minimizing potential errors or inefficiencies. Through this effort a flexible and continuously evolving synthesis module is envisioned, aiming at significantly enhancing WSNs' user friendliness, practicality, efficiency and thus the widespread use of WSN deployments. © 2013 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Virtual road signs: Augmented reality driving aid for novice drivers

Virtual road signs: Augmented reality driving aid for novice...

引用

Human Factors and Ergonomics Society 2016 International Annual Meeting, HFES 2016

作者： Rane, Prerana Kim, Hyungil Marcano, Juan Lopez Gabbard, Joseph L. Department of Electrical and Computer United States Industrial and Systems Engineering Virginia Tech United States

Studies have shown that experts are more sensitive to changes in the road scene than novice drivers, and use the driving patterns of other cars to infer important information. A tool that can help bridge the gap between experts and novices may be augmented reality (AR), which can be used to graphically overlay virtual information onto the real world that may not otherwise be easily inferred. In this paper, we propose an AR interface that aims to improve the sensation, attention, situation awareness and decision making of international drivers who are new to the United States (US). We present results of a preliminary study that identifies the needs of novice international drivers as well as an AR interface design created to support these needs. Contextual inquiry and analysis techniques were used to extract the needs of novice international drivers. Based on observations, iterative designs and a prototype were developed that merge AR and audio feedback. Lastly, the prototype was evaluated by two usability experts, who performed a heuristic walkthrough based on the principles of human information processing. The experts conclude that the interface has the potential of increasing the sensation, attention, situation awareness and decision making while reducing the mental workload of novice international drivers. Future work will include an empirical study to support the observations of the analytical evaluation presented herein. Copyright 2016 by Human Factors and Ergonomics Society.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

APECS: Adaptive Personalized Control System Architecture

arXiv

引用

arXiv 2025年

作者： Juston, Marius F.R. Gisi, Alex Norris, William R. Nottage, Dustin Soylemezoglu, Ahmet The Grainger College of Engineering Industrial and Enterprise Systems Engineering Department University of Illinois Urbana-Champaign UrbanaIL61801-3080 United States The Grainger College of Engineering Electrical and Computer Engineering Department University of Illinois Urbana-Champaign UrbanaIL61801-3080 United States Construction Engineering Research Laboratory U.S. Army Corps of Engineers Engineering Research and Development Center IL61822 United States

This paper presents the Adaptive Personalized Control System (APECS) architecture, a novel framework for human-in-the-loop control. An architecture is developed which defines appropriate constraints for the system objectives. A method for enacting Lipschitz and sector bounds on the resulting controller is derived to ensure desirable control properties. An analysis of worst-case loss functions and the optimal loss function weighting is made to implement an effective training scheme. Finally, simulations are carried out to demonstrate the effectiveness of the proposed architecture. This architecture resulted in a 4.5% performance increase compared to the human operator and 9% to an unconstrained feedforward neural network trained in the same way. © 2025, CC BY.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Human Factors in Virtual Reality System Design for Mobility and Haptic Task Performance

引用

Reviews of Human Factors and Ergonomics 2011年第1期7卷 323-366页

作者： Kaber, David B. Zhang, Tao Department of Industrial and Systems Engineering North Carolina State University United States Department of Electrical Engineering Computer Science at Vanderbilt University United States

In this chapter, we review research on the use of virtual reality (VR) and haptic technologies for studying human performance in tasks involving the tactile sense, including locomotion and upper-extremity motor-control training or rehabilitation. We present a general organizing framework of motor-control tasks and identify types of VR systems that have been developed for supporting the tactile sense in simulation of such tasks. We divide this coverage into gross motor tasks with a focus on locomotion and gait, in part because of the volume of research that has been conducted in this area, and fine motor skills with a focus on training for surgical tasks and upper-extremity rehabilitation. In covering VR technology, we review visual devices that facilitate hand-eye or body-eye coordination as well as physical task simulators (e.g., treadmill interfaces and haptic controllers). The directions of locomotion and motor-control task research exploiting these technologies are identified, and seminal studies representing each area are summarized. On this basis, we define a collection of VR simulation design recommendations from task and functional perspectives. The review also identifies the underlying cognitive and physical bases for specific observations on human performance made by previous research. Finally, the summaries of research studies are used as a basis for identifying future directions of research that should be addressed by the human factors community. © 2011 by Human Factors and Ergonomics Society.

关键词： haptic devices locomotion motor control rehabilitation surgical simulation virtual reality

来源：评论

学校读者我要写书评

暂无评论

EV Adoption Impacts on Residential, Commercial and Urban-Commercial Feeders

EV Adoption Impacts on Residential, Commercial and Urban-Com...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Ravi, Abhijith Bai, Linquan Wollam, Grant Enslin, Johan Unc Charlotte Industrial and Systems Engineering Charlotte United States Clemson University Electrical and Computer Engineering Clemson United States

ISBN: (纸本)9798350316445

This paper analyzes the impacts of electric vehicle (EV) adoption on real distribution networks and compares mitigation options at the distribution level. The impact of EV adoption on residential, commercial, and urban-commercial feeders was analyzed. EV load growth rates and feeder load profiles were extracted as inputs to scale up the effects of adoption. Various mitigation options, such as conventional system upgrades, battery energy storage systems, and time of use for all feeders, were compared. The results show that managed charging is likely to be adopted by commercial fleets, as they can be controlled by charging management systems to reduce peak demand. Commercial fleets can play a vital role in peak load shifting and overload mitigation if appropriately incentivized. © 2023 IEEE.

关键词： distribution grid electric vehicles fleets grid vulnerabilities mitigation time of use

来源：评论

学校读者我要写书评

暂无评论

Detecting sponsored recommendations

引用

ACM Transactions on Modeling and Performance Evaluation of Computing systems 2016年第1期2卷 1–29页

作者： Krishnasamy, Subhashini Sen, Rajat Shakkottai, Sanjay Oh, Sewoong Department of Electrical and Computer Engineering University of Texas at Austin AustinTX78701 United States Industrial and Enterprise Systems Engineering Department University of Illinois at Urbana-Champaign UrbanaIL61801 United States

With the vast number of items, Web pages, and news from which to choose, online services and customers both benefit tremendously from personalized recommender systems. Such systems additionally provide great opportunities for targeted advertisements by displaying ads alongside genuine recommendations. We consider a biased recommendation system in which such ads are displayed without any tags (disguised as genuine recommendations), rendering them indistinguishable to a single user. We ask whether it is possible for a small subset of collaborating users to detect such bias. We propose an algorithm that can detect this type of bias through statistical analysis on the collaborating users' feedback. The algorithm requires only binary information indicating whether a user was satisfied with each of the recommended item or not. This makes the algorithm widely appealing to real-world issues such as identification of search engine bias and pharmaceutical lobbying. We prove that the proposed algorithm detects the bias with high probability for a broad class of recommendation systems when a sufficient number of users provides feedback on a sufficient number of recommendations. We provide extensive simulations with real datasets and practical recommender systems, which confirm the trade-offs in the theoretical guarantees. © 2016 ACM

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Photogrammetry for Digital Twinning Industry 4.0 (I4) systems 21

Photogrammetry for Digital Twinning Industry 4.0 (I4) System...

引用

2024 IEEE/ACS 21st International Conference on computer systems and Applications, AICCSA 2024

作者： Alhamadah, Ahmed Mamun, Muntasir Harms, Henry Redondo, Mathew Lin, Yu-Zheng Pacheco, Jesus Salehi, Soheil Satam, Pratik University of Arizona Department of Systems and Industrial Engineering United States University of Arizona Department of Electrical and Computer Engineering United States School of Industrial Engineering University of Sonora Mexico

ISBN: (纸本)9798331518240

The onset of Industry 4.0 is rapidly transforming the manufacturing world through the integration of cloud computing, machine learning (ML), artificial intelligence (AI), and universal network connectivity, resulting in performance optimization and increased productivity. Digital Twins (DT) are one such transformational technology that leverages software systems to replicate physical process behavior, and representing it in a digital environment. This paper aims to explore the use of photogrammetry (which is the process of reconstructing physical objects into virtual 3D models using photographs) and 3D Scanning techniques to create accurate visual representation of the 'Physical Process', to interact with the ML/AI based behavior models. To achieve this, we have used a readily available consumer device, the iPhone 15 Pro, which features stereo vision capabilities, to capture the depth of an Industry 4.0 system. By processing these images using 3D scanning tools, we created a raw 3D model for 3D modeling and rendering software for the creation of a DT model. The paper highlights the reliability of this method by measuring the error rate in between the ground truth (measurements done manually using a tape measure) and the final 3D model created using this method. The overall mean error is 4.97 % and the overall standard deviation error is 5.54% between the ground truth measurements and their photogrammetry counterparts. The results from this work indicate that photogrammetry using consumer-grade devices can be an efficient and cost-efficient approach to creating DTs for smart manufacturing, while the approaches flexibility allows for iterative improvements of the models over time. © 2024 IEEE.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

A farewell to the bias-variance tradeoff? An overview of the theory of overparameterized machine learning

arXiv

引用

arXiv 2021年

作者： Dar, Yehuda Muthukumar, Vidya Baraniuk, Richard G. Electrical and Computer Engineering Department Rice University Schools of Electrical and Computer Engineering and Industrial and Systems Engineering Georgia Institute of Technology

The rapid recent progress in machine learning (ML) has raised a number of scientific questions that challenge the longstanding dogma of the field. One of the most important riddles is the good empirical generalization of overparameterized models. Overparameterized models are excessively complex with respect to the size of the training dataset, which results in them perfectly fitting (i.e., interpolating) the training data, which is usually noisy. Such interpolation of noisy data is traditionally associated with detrimental overfitting, and yet a wide range of interpolating models – from simple linear models to deep neural networks – have recently been observed to generalize extremely well on fresh test data. Indeed, the recently discovered double descent phenomenon has revealed that highly overparameterized models often improve over the best underparameterized model in test performance. Understanding learning in this overparameterized regime requires new theory and foundational empirical studies, even for the simplest case of the linear model. The underpinnings of this understanding have been laid in very recent analyses of overparameterized linear regression and related statistical learning tasks, which resulted in precise analytic characterizations of double descent. This paper provides a succinct overview of this emerging theory of overparameterized ML (henceforth abbreviated as TOPML) that explains these recent findings through a statistical signal processing perspective. We emphasize the unique aspects that define the TOPML research area as a subfield of modern ML theory and outline interesting open questions that remain. Copyright © 2021, The Authors. All rights reserved.

关键词： Interpolation

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：