检索结果-内蒙古大学图书馆

Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 1745-1757页

作者： Hong, Qian-Bei Wu, Chung-Hsien Wang, Hsin-Min National Cheng Kung University and Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701 Taiwan Academia Sinica Taipei115 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Academia Sinica Institute of Information Science Taipei115 Taiwan

Speech content is closely related to the stability of speaker embeddings in speaker verification tasks. In this paper, we propose a novel architecture based on self-constraint learning (SCL) and reconstruction task (RT) to remove the influence of phonetic information on speaker embedding generation. First, SCL is used to reduce the divergence of frame-level features, which can avoid ambiguity between the resulting embeddings of the two utterances being compared. Second, RT is used to further remove phonetic information in frame-level layers, focusing on speaker-discriminative feature transformation. In our experiments, the speaker embedding models were trained on the VoxCeleb2 dataset and evaluated on the VoxCeleb1, Librispeech, SITW and VoxMovies datasets. Experimental results on VoxCeleb1 show that the proposed DROP-TDNN system reduced the EER by 7.5%, compared to the state-of-the-art ECAPA-TDNN system. Furthermore, the proposed DROP-TDNN system also outperformed the ECAPA-TDNN system in the experiments on SITW, Librispeech and VoxMovies under cross-dataset conditions. In the experiments on SITW, the proposed system reduced the EER by 3.4% compared to the ECAPA-TDNN system. In the experiments on Librispeech, the proposed system demonstrated the advantage of removing phonetic information under the clean speech condition, with a significant reduction of 25.5% in EER compared to the ECAPA-TDNN system. In the experiments on VoxMovies, the proposed system reduced the EER by up to 7.9% compared to the ECAPA-TDNN system under different pronunciation and background conditions. © 2014 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Smart Dome 4.0: Low-Cost, Independent, Automated Energy System for Agricultural Purposes enabled by Machine Learning 2

Smart Dome 4.0: Low-Cost, Independent, Automated Energy Syst...

引用

2021 2nd International Symposium on Automation, Information and Computing, ISAIC 2021

作者： Budiman, Arief S Gunawan, Fergyanto Djuana, Endang Pardamean, Bens Romeli, Sugiarto Putri, Dianing Nn Aji, Daisman Pb Rahardjo, Kuat Stevanus Ilham Wibowo, M. Daffa, Nadiev Owen, Raymond Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Department of Manufacturing and Mechanical Engineering and Technology Oregon Institute of Technology Klamath FallsOR97601 United States Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia PT. Impack Pratama Industri Tbk Jakarta Indonesia Mechanical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta Indonesia Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia

Many economically essential crops in Indonesia (such as coffee, tea, chocolate, or copra) require storage or drying under certain environmental conditions, especially temperature and humidity. The solar dryer dome, typically used for agricultural purposes in Indonesia, produces a sufficient amount of heat to increase the evaporation rate inside the dome and reduce the moisture content of the commodity. A hybrid solar dryer accompanied by a photovoltaic panel, fan, and ventilation system is generally suitable. The system can provide an optimum environment with minimum control. However, as the outdoor temperature and humidity change dramatically, such as at night time, more control is required. Based on Industry 4.0 technologies, we have developed a new kind of hybrid solar dryer that provides an optimum environment 24/7. The system, called Smart Dome 4.0, is an intelligent, low-cost, self-sufficient drying and storage system to support Indonesia Agriculture 4.0. The system has a local power generation unit to self-sustain the required energy and operate without connecting to the electricity grid. The system utilizes a machine-learning algorithm to predict the environmental condition and optimally uses self-generated electric power. The developed Smart Dome 4.0 technology is critical to producing a sustainable solar dome under drastic environmental dynamics. © Published under licence by IOP Publishing Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Self-Tunable Nonlinear Generation in Metasurfaces

Self-Tunable Nonlinear Generation in Metasurfaces

引用

CLEO: Fundamental Science, CLEO:FS 2024 - Part of Conference on Lasers and Electro-Optics, CLEO 2024

作者： Almeida, Euclides Feinstein, Matthew Blechman, Yael Andronikides, Alexander Queens College City University of New York FlushingNY11367 United States The Graduate Center of the City University of New York New YorkNY10016 United States Andrew and Erna Viterbi Department of Electrical and Computer Engineering Technion Israel Institute of Technology Haifa32000 Israel

We realize a frequency-converting nonlinear metasurface that can be self-tuned by pumping with strong fields. The tunability is attained via quantum nonlinearities, opening up new ways of engineering quantum effects i... 详细信息

ISBN: (纸本)9781957171395

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE CONTINUAL LEARNING 11

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Jung, Dahuin Lee, Dongjin Hong, Sunwon Jang, Hyemi Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of DeepBrain AI Inc. Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adaptation network (MuFAN) that utilizes a richer context encoding extracted from different levels of a pre-trained network. Additionally, we introduce a novel structure-wise distillation loss and replace the commonly used batch normalization layer with a newly proposed stability-plasticity normalization module to train MuFAN that simultaneously maintains high plasticity and stability. MuFAN outperforms other state-of-the-art continual learning methods on the SVHN, CIFAR100, miniImageNet, and CORe50 datasets. Extensive experiments and ablation studies validate the significance and scalability of each proposed component: 1) multi-scale feature maps from a pre-trained encoder, 2) the structure-wise distillation loss, and 3) the stability-plasticity normalization module in MuFAN. Code is publicly available at https://***/whitesnowdrop/MuFAN. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context

arXiv

引用

arXiv 2024年

作者： Yu, Sangwon Kim, Ik-Hwan Song, Jongyoon Lee, Saehyung Park, Junsung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often struggle to filter out irrelevant documents within the context, and their performance is sensitive to the position of supporting documents within that context. In this paper, we identify an additional challenge: LLMs' performance is also sensitive to the order in which the supporting documents are presented. We refer to this as the misordered context problem. To address this issue, we propose a simple yet effective method called context repetition (CoRe), which involves prompting the model by repeatedly presenting the context to ensure the supporting documents are presented in the optimal order for the model. Using CoRe, we improve the F1 score by up to 30%p on multi-hop QA tasks and increase accuracy by up to 70%p on a synthetic task. Additionally, CoRe helps mitigate the well-known "lost-in-the-middle" problem in LLMs and can be effectively combined with retrieval-based approaches utilizing Chainof- Thought (CoT) reasoning. Copyright © 2024, The Authors. All rights reserved.

关键词： Context sensitive languages

来源：评论

学校读者我要写书评

暂无评论

Real-time Vehicle Detection and Tracking on Fisheye Traffic Monitoring Video in Compressed Domain

引用

APSIPA Transactions on Signal and Information Processing 2023年第4期12卷

作者： Ardianto, Sandy Hang, Hsueh-Ming Cheng, Wen-Huang Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

Our goal is to develop real-time vehicle detection and tracking schemes for fisheye traffic monitoring video using the temporal information in the compressed domain without decoding the entire video. Two algorithms are proposed. The first algorithm starts with a conventional single-frame detector, but we introduce a multi-frame information fusion stage to improve the final detection and tracking accuracy, which is implemented using multi-modal bi-directional LSTM (MM bi-LSTM) network. The second algorithm first constructs multi-frame motion trail image, and then a single-image multi-head detector is designed to produce bounding boxes of an individual frame. The first scheme can be viewed as a detect-to-track design, and the second scheme is track-to-detect. We tested our proposals on the ICIP2020 VIP Cup dataset in H.265 video format. The aforementioned algorithms are applied to the motion fields and residual images in the H.265 compressed data set. It turns out that their detection and tracking performances are on par with their pixel-domain counterparts, and they can achieve the state-of-the-art accuracy of conventional video object detectors and trackers. If the decoding process for video compression is not counted, their computational complexities are much lower than the conventional pixel-domain video object detectors and trackers. © 2023 S. Ardianto, H.-M. Hang and W.-H. Cheng.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

YOLO Instance Segmentation Model Comparison for Drone Detection as Visual Servo Control Marker

YOLO Instance Segmentation Model Comparison for Drone Detect...

引用

International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)

作者： John Mel A. Bolaybolay Earl Ryan M. Aleluya Steve E. Clar Jeanette C. Pao Carl John O. Salaan Prancis Jann A. Alagon Cherry Mae G. Villame Sherwin A. Guirnaldo Department of Electrical Engineering Department of Computer Engineering and Mechatronics Graduate School of Engineering Department of Mechanical Engineering and Technology Mindanao State University - Iligan Institute of Technology Iligan City Philippines

ISBN: (数字)9798350381177

ISBN: (纸本)9798350381184

The development of collaborative aerial and ground robot technology offers a promising solution for volcano-exploring robotic systems. However, certain components are missing, particularly concerning the concept of ground robot retrieval. While the use of visual servo control is not new, it can be applied for aligning drones and rovers to facilitate ground robot retrieval. Traditional visual servo control methods often rely on fiducial markers, which may lack robustness in practical implementations. Within this paper, the authors propose an alternative visual servo control marker suitable for real-world scenarios. We present a comparative analysis of existing instance seg-mentation models from different YOLO versions, specifically, YOLOvS, YOLOv7, and YOLOv8, trained for drone detection. Additionally, we introduce a novel dataset, DroneCVS, comprising drone images captured from the ground robot's perspective under varying weather and altitude conditions. Our experimental findings demonstrate the instance segmentation model's capacity to acquire and learn drone segmentation from the DroneCVS dataset, achieving outstanding performance in different in evaluation metrics. In most evaluation scenarios, YOLOvS outperforms other models, leading to the conclusion that it provides the best balance between speed, weight, and performance in real-time applications.

关键词： YOLO Instance segmentation Measurement Visualization Fiducial markers Servosystems Robots

来源：评论

学校读者我要写书评

暂无评论

A Survey of Camouflaged Object Detection and Beyond

引用

CAAI Artificial Intelligence Research 2024年第1期3卷 1-30页

作者： Fengyang Xiao Sujie Hu Yuqi Shen Chengyu Fang Jinfa Huang Longxiang Tang Ziyun Yang Xiu Li Chunming He Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Department of Biomedical Engineering Duke UniversityDurhamNC 27708USA School of Electrical and Computer Engineering Peking UniversityShenzhen 518055China

Camouflaged object detection(COD)refers to the task of identifying and segmenting objects that blend seamlessly into their surroundings,posing a significant challenge for computer vision *** recent years,COD has garnered widespread attention due to its potential applications in surveillance,wildlife conservation,autonomous systems,and *** several surveys on COD exist,they often have limitations in terms of the number and scope of papers covered,particularly regarding the rapid advancements made in the field since *** address this void,we present the most comprehensive review of COD to date,encompassing both theoretical frameworks and practical contributions to the *** paper explores various COD methods across four domains,including both image-level and video-level solutions,from the perspectives of traditional and deep learning *** thoroughly investigate the correlations between COD and other camouflaged scenario methods,thereby laying the theoretical foundation for subsequent ***,we delve into novel tasks such as referring-based COD and collaborative COD,which have not been fully addressed in previous *** object-level detection,we also summarize extended methods for instance-level tasks,including camouflaged instance segmentation,counting,and ***,we provide an overview of commonly used benchmarks and evaluation metrics in COD tasks,conducting a comprehensive evaluation of deep learning-based techniques in both image and video domains,considering both qualitative and quantitative ***,we discuss the limitations of current COD models and propose 9 promising directions for future research,focusing on addressing inherent challenges and exploring novel,meaningful *** comprehensive examination aims to deepen the understanding of COD models and related methods in camouflaged *** those interested,a curated list of CODrelated techniques,datasets,and addit

关键词： camouflaged object detection camouflaged scenario understanding deep learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Wideband Beamforming for Frequency Selective RRS Aided Near-Field Communications

Wideband Beamforming for Frequency Selective RRS Aided Near-...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Lin, Zicheng Zeng, Shuhao Zhang, Hongliang School of Electronic Engineering and Computer Science Peking University Beijing China Princeton University Department of Electrical and Computer Engineering NJ United States School of Electronic and Computer Engineering Peking University Shenzhen Graduate School China School of Electronics Peking University Beijing China

ISBN: (纸本)9798350368369

To satisfy the high data rate requirements, cellular systems will evolve towards the direction of higher carrier frequencies and larger antenna arrays. The conventional phased arrays are hard to fulfill such a vision due to its excessive power consumption induced by numerous phase shifters. To address this issue, Reconfigurable Refractive Surfaces (RRSs) provide a energy efficient solution without relying on phase shifters. With enlarged radiation aperture and increased working frequency, users are more likely to be located in the near field of the RRS. Moreover, the frequency selectivity of the RRS cannot be neglected given the wideband communications enabled by higher frequency bands. These two effects jointly aggravate the beam split problem where the signal strength of different frequency components cannot concentrate on the user, leading to a data rate degradation. In this paper, we study an RRS-based wideband near-field communication system with multiple users. Unlike most existing works, which only considered the beam split effect under near-field conditions, we jointly consider the influence of the frequency selectivity of RRS and near-field conditions on the beam split effect. To mitigate the beam split effect, the time-delay units are introduced in the RRS elements based on which a beamforming scheme is proposed to improve system data rate by jointly optimizing the digital beamformer, the phase shifts of RRS and the time-delay units. Simulation results demonstrate the effectiveness of our proposed scheme. © 2025 IEEE.

关键词： Antenna phased arrays

来源：评论

学校读者我要写书评

暂无评论

MultiWienerNet: Deep learning for fast shift-varying deconvolution

MultiWienerNet: Deep learning for fast shift-varying deconvo...

引用

Computational Optical Sensing and Imaging, COSI 2021 - Part of OSA Imaging and Applied Optics Congress 2021

作者： Shuai, Richard W. Yanny, Kyrollos Monakhova, Kristina Waller, Laura Department of Electrical Engineering and Computer Sciences University of California Berkeley United States UCB/UCSF Joint Graduate Program in Bioengineering University of California Berkeley United States

We present a deep-learning method based on Wiener filters and U-Nets that performs image reconstruction in systems with spatially-varying aberrations. We train on simulated microscopy measurements and test on experime... 详细信息

ISBN: (纸本)9781557528209

关键词： Image reconstruction

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：