检索结果-内蒙古大学图书馆

Parallel Synthesis for Autoregressive Speech Generation

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 3095-3111页

作者： Hsu, Po-Chun Liu, Da-Rong Liu, Andy T. Lee, Hung-Yi National Taiwan University Graduate Institute of Communication Engineering College of Electrical Engineering and Computer Science Taipei10617 Taiwan

Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time steps. Though it synthesizes natural human speech, the iterative generation inevitably makes the synthesis time proportional to the utterance length, leading to low efficiency. Many works were dedicated to generating the whole speech sequence in parallel and proposed GAN-based, flow-based, and score-based vocoders. This paper proposed a new thought for the autoregressive generation. Instead of iteratively predicting samples in a time sequence, the proposed model performs frequency-wise autoregressive generation (FAR) and bit-wise autoregressive generation (BAR) to synthesize speech. In FAR, a speech utterance is split into frequency subbands, and a subband is generated conditioned on the previously generated one. Similarly, in BAR, an 8-bit quantized signal is generated iteratively from the first bit. By redesigning the autoregressive method to compute in domains other than the time domain, the number of iterations in the proposed model is no longer proportional to the utterance length but to the number of subbands/bits, significantly increasing inference efficiency. Besides, a post-filter is employed to sample signals from output posteriors;its training objective is designed based on the characteristics of the proposed methods. Experimental results show that the proposed model can synthesize speech faster than real-time without GPU acceleration. Compared with baseline vocoders, the proposed model achieves better MUSHRA results and shows good generalization ability for unseen speakers and 44 kHz speech. © 2014 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

CC-YOLO: An Improved PCB Surface Defect Detection Model for YOLOv7 5

CC-YOLO: An Improved PCB Surface Defect Detection Model for ...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Yi, Xiangyu Song, Xudong Dalian Jiaotong University Computer and Communication Engineering Institute Dalian China

ISBN: (纸本)9798350373820

Recently, there has been increasing academic interest in the problem of detecting surface defects on PCBs due to their significance in manufacturing processes. To address the issue of low detection accuracy in existing PCB surface defect detection models, this paper introduces a novel model called CC-YOLO, which enhances YOLOv7. The proposed model incorporates the CARAFE (Content-Aware ReAssembly of FEatures) operator as an up-sampling technique to minimize feature information loss in the input image and enhance the model's feature extraction capability. Additionally, we propose the C2f-C module, which extends CSPDarknet53 to 2-Stage FPN-Cascade and strengthens it further by incorporating multiple Bottleneck modules to capture more comprehensive gradient flow information. We evaluate the performance of the enhanced YOLOv7-based model, CC-YOLO, on the publicly available PCB surface defect dataset from the Intelligent Robotics Laboratory at Peking University. The experimental results demonstrate that CC-YOLO achieves an accuracy of 9 8. 9%, 2.3% higher than the original YOLOv7 model. © 2024 IEEE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

CSTformer: Cross Spatio-Temporal Transformer for Multivariate Time Series Forecasting

CSTformer: Cross Spatio-Temporal Transformer for Multivariat...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Cai, Tao Wu, Haixiang Niu, Dejiao Li, Lei Computer Science and Communication Engineering Institute of Jiangsu University Zhenjiang China

ISBN: (纸本)9781665410205

Transformer-based models have shown remarkable success in Multivariate Time Series Forecasting (MTSF). Previous methods apply Attention mechanisms to capture temporal and spatial (variable) dependencies separately. However, they struggle to model intricate local spatiotemporal correlations. To address this limitation and enhance performance, we propose CSTformer, a novel Transformer-based model that enables capturing Cross Spatio- Temporal (CST) dependency for MTSF. In CSTformer, through a Variate Compete Linear Attention (VCLA) mechanism, each variable efficiently achieves specific CST features, which compete against the backdrop of the local multivariate. Additionally, we develop a Mixture of Latent (MoL) module to provide adaptive predictions for variables with varying degrees of CST dependencies. Our experimental results on nine benchmarks indicate that, compared with the state-of-the-art method, CSTformer yields a 2.7% relative improvement. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

DC-YOLO: A dual channel YOLO for small object defect detection of circuit boards 5

DC-YOLO: A dual channel YOLO for small object defect detecti...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wang, Haoyu Song, Xudong Dalian Jiaotong University Computer and Communication Engineering Institute Dalian China

ISBN: (纸本)9798350373820

In response to the limitations of existing circuit board defect detection methods, including low detection efficiency, severe leakage of small-sized defects, and incomplete feature capture, this paper proposes an enhanced defect detection network called DC-YOLO based on YOLOv7. Firstly, a spatial pooling pyramid, DC-SPPFCSPC, is constructed in this paper. It combines multi-dimensional salient features with global spatial features by extracting and locating a dual-channel structure. The enhancement focuses on establishing the measured connection between defective points and the global features while preserving the spatial attributes of deep image features. Secondly, the model improves the FPN by fusing higher dimensional features. This enhancement enriches the shallow feature information without altering the original number of detection heads. Consequently, this method retains more relevant information while avoiding increasing the burden on the detection head. Lastly, CBAM is integrated into the FPN input. This integration enhances the algorithm's ability to concentrate on the defective area, providing more detailed feature information. The experimental results indicate that the mAP of the enhanced algorithm reached 98.39% and 98.56% respectively on the public dataset and the dataset with defective homemade circuit boards. There was a significant improvement in small object detection. © 2024 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Efficient resource allocation for D2D-enabled social IoT networks:A tripartite and time-scale optimization approach

引用

Intelligent and Converged Networks 2024年第4期5卷 380-401页

作者： Saurabh Chandra Rajeev Arya Maheshwari Prasad Singh Department of Electronics&Communication Engineering National Institute of Technology PatnaPatna 800005India Department of Computer Science and Engineering National Institute of Technology PatnaPatna 800005India

In the densification of Device-to-Device(D2D)-enabled Social Internet of Things(SIoT)networks,improper allocation of resources can lead to high interference,increased signaling overhead,latency,and disruption of Channel State Information(CSI).In this paper,we formulate the problem of sum throughput maximization as a Mixed Integer Non-Linear Programming(MINLP)*** problem is solved in two stages:a tripartite graph-based resource allocation stage and a time-scale optimization *** proposed approach prioritizes maintaining Quality of Service(QoS)and resource allocation to minimize power consumption while maximizing sum *** results demonstrate the superiority of the proposed algorithm over standard benchmark *** of the proposed algorithm using performance parameters such as sum throughput shows improvements ranging from 17%to 93%.Additionally,the average time to deliver resources to CSI users is minimized by 60.83%through optimal power *** approach ensures QoS requirements are met,reduces system signaling overhead,and significantly increases D2D sum throughput compared to the state-of-the-art *** proposed methodology may be well-suited to address the challenges SIoT applications,such as home automation and higher education systems.

关键词： Device-to-Device(D2D)communication Social Internet of Things(SIoT) resource allocation Quality of Service(QoS) tripartite graph time scale

来源：评论

学校读者我要写书评

暂无评论

Two-Dimensional Golay Complementary Array Sets with Arbitrary Lengths for Omnidirectional MIMO Transmission

引用

IEEE Transactions on communications 2024年第2期72卷 1135-1145页

作者： Zhao, You-Qi Pai, Cheng-Yu Huang, Zhen-Ming Liu, Zilong Chen, Chao-Yu National Cheng Kung University Department of Engineering Science Tainan701 Taiwan National Cheng Kung University Department of Engineering Science and the Institute of Computer and Communication Engineering Tainan701 Taiwan University of Essex School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom National Cheng Kung University Department of Electrical Engineering and the Institute of Computer and Communication Engineering Tainan701 Taiwan

This paper presents a coding approach for achieving omnidirectional transmission of certain common signals in massive multi-input multi-output (MIMO) networks such that the received power at any direction in a cell remains constant for any given distance. Specifically, two-dimensional (2D) Golay complementary array set (GCAS) can be used to design the massive MIMO precoding matrix so as to achieve omnidirectional transmission due to its complementary autocorrelation property. In this paper, novel constructions of new 2D GCASs with arbitrary array lengths are proposed. Our key idea is to carefully truncate the columns of certain larger arrays generated by 2D generalized Boolean functions. Finally, the power radiation patterns and numerical results are provided to verify the omnidirectional property of the GCAS-based precoding. The error performances of the proposed precoding scheme are presented to validate its superiority over the existing alternatives. © 1972-2012 IEEE.

关键词： Peak to average power ratio

来源：评论

学校读者我要写书评

暂无评论

Noise Estimation from Degraded Speech

Noise Estimation from Degraded Speech

引用

International Conference on 6G communications Networking and Signal Processing, SGCNSP 2023

作者： Thorbole, Shubham Raj, Rahul Upadhyay, Navneet Department of Electronics and Communication Engineering The LNM Institute of Information Technology Jaipur India Department of Computer and Communication Engineering The LNM Institute of Information Technology Jaipur India

ISBN: (纸本)9789819778751

In real-world scenarios, speech signals are often corrupted by various types of noise, which can significantly degrade the intelligibility and quality of the speech. Noise in such environments is highly non-stationary, changing rapidly and unpredictably. A new algorithm has been created to estimate noise in speech signals affected by rapidly changing and unpredictable non-stationary noise. This algorithm aims to enhance speech quality and intelligibility in challenging acoustic settings. It determines signal presence by comparing the power spectrum of noisy speech to a continually updated local minimum, calculated from past noisy speech power spectra with a look-ahead factor. Its standout feature is its rapid adaptability to swiftly respond to new noise patterns, crucial for maintaining speech clarity and quality in dynamic noise environments. Formal experiments validated its effectiveness compared to other noise-estimation methods when integrated into speech enhancement systems, using metrics like mean squared error (MSE) and signal to noise ratio (SNR). This algorithm significantly contributes to noise estimation and voice enhancement, offering effectiveness in handling highly non-stationary noise and being adaptable and versatile for various applications. This algorithm stands as a substantial advancement in the domains of noise estimation and voice enhancement overall. Its utility extends across diverse applications owing to its proficiency in handling highly non-stationary noise conditions, coupled with its adaptability and versatility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Improved Load-Balanced Clustering for Energy-Aware Routing(ILBC-EAR)in WSNs

引用

computer Systems Science & engineering 2023年第1期44卷 99-112页

作者： D.Loganathan M.Balasubramani R.Sabitha S.Karthik Department of Electronics and Communication Engineering Info Institute of EngineeringCoimbatore641107India Department of Computer Science and Engineering SNS College of TechnologyCoimbatore641035India

Sensors are considered as important elements of electronic *** many applications and service,Wireless Sensor Networks(WSNs)are involved in significant data sharing that are delivered to the sink node in energy efficient man-ner using multi-hop ***,the major challenge in WSN is the nodes are having limited battery resources,it is important to monitor the consumption rate of energy is very much ***,reducing energy con-sumption can increase the network lifetime in effective *** that,clustering methods are widely used for optimizing the rate of energy consumption among the sensor *** that concern,this paper involves in deriving a novel model called Improved Load-Balanced Clustering for Energy-Aware Routing(ILBC-EAR),which mainly concentrates on optimal energy utilization with load-balanced process among cluster heads and member *** providing equal rate of energy consumption among nodes,the dimensions of framed clusters are ***,the model develops a Finest Routing Scheme based on Load-Balanced Clustering to transmit the sensed information to the sink or base *** evaluation results depict that the derived energy aware model attains higher rate of life time than other works and also achieves balanced energy rate among head ***,the model also provides higher throughput and minimal delay in delivering data packets.

关键词： Wireless sensor networks energy consumption load balanced clustering finest routing

来源：评论

学校读者我要写书评

暂无评论

Maximizing Learning Outcomes while Minimizing: Costs: A Cost-Effective Approach to M-Learning

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第11期18卷 4-14页

作者： Suresh Kumar, B. Hemawathi, M.S. Dhanasekaran, P. Kaliappan, Vishnu Kumar Sivaganesan, D. Department of Electronics and Communication Engineering The Kavery Engineering College Tamil Nadu Salem India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Tamil Nadu Coimbatore India

In the realm of education, the pursuit of effective learning outcomes often faces the challenge of limited resources. This paper explores the intersection of maximizing learning outcomes and minimizing costs through a cost-effective approach to mobile learning (m-learning). Recognizing the ubiquitous presence of mobile devices and their potential to revolutionize learning, this study explores strategies that leverage the capabilities of mobile technology while being mindful of budgetary constraints. By leveraging the flexibility and accessibil- ity offered by m-learning platforms, educators can design engaging and interactive learning experiences that cater to diverse learners needs. The paper investigates various cost-effective methodologies, including utilizing open-source software, repurposing existing resources, and adopting collaborative learning environments. Furthermore, it examines the role of scalable technologies and adaptive learning algorithms in optimizing resource allocation and per- sonalizing learning experiences. Through case studies and empirical analysis, this research illustrates how institutions and educators can achieve significant cost savings without com- promising the quality of educational delivery. Ultimately, the findings highlight the transfor- mative potential of a cost-effective approach to m-learning in enhancing learning outcomes and widening access to education. © 2024 by the authors of this article.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FusionEXNet: an interpretable fused deep learning model for skin cancer detection

引用

International Journal of computers and Applications 2024年第9期46卷 743-753页

作者： Gautam, Yuvika Gupta, Piyush Kumar, Deepika Kalra, Bhavya Kumar, Abhinav Hemanth, Jude D. Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Electronics & Communication Engineering Karunya Institute of Technology and Sciences Coimbatore India

Skin cancer poses a significant burden on mankind and healthcare systems globally, necessitating the development of effective diagnostic and treatment strategies. This paper introduces FusionEXNet, an innovative and interpretable fused deep-learning model for skin cancer detection. FusionEXNet leverages the strengths of EfficientNetV2S and XceptionNet architectures to extract robust features from dermoscopic images, achieving superior performance compared to individual models. While XceptionNet and EfficientNetV2S attained accuracies of 88.82% and 88.01%, respectively, FusionEXNet surpassed them with an impressive accuracy of 90.83%. To enhance model interpretability, Explainable Artificial Intelligence (XAI) techniques, such as SmoothGrad and Faster Score-CAM, are integrated, providing valuable insights into the decision-making process. The model was trained and evaluated using the extensive HAM10000 dataset, consisting of over 10,000 high-resolution images across seven skin lesion categories. The proposed FusionEXNet model offers a reliable, accurate, and interpretable system for skin cancer detection, contributing to improved patient outcomes and more efficient diagnostic processes. This study underscores the potential of combining advanced CNN architectures with XAI methods to create powerful tools for dermatological diagnostics. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Deep learning

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：