检索结果-内蒙古大学图书馆

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Jialu Li Mark Hasegawa-Johnson Nancy L. McElwain Department of Electrical and Computer Engineering University of Illinois Beckman Institute for Advanced Science and Technology University of Illinois Department of Human Development and Family Studies University of Illinois

ISBN: (数字)9798350374513

ISBN: (纸本)9798350374520

To understand why self-supervised learning (SSL) models have empirically achieved strong performances on several speech-processing downstream tasks, numerous studies have focused on analyzing the encoded information of the SSL layer representations in adult speech. Limited work has investigated how pre-training and fine-tuning affect SSL models encoding children's speech and vocalizations. In this study, we aim to bridge this gap by probing SSL models on two relevant downstream tasks: (1) phoneme recognition (PR) on the speech of adults, older children (8-10 years old), and younger children (1-4 years old), and (2) vocalization classification (VC) distinguishing cry, fuss, and babble for infants under 14 months old. For younger children's PR, the superiority of fine-tuned SSL models is largely due to their ability to learn features that represent older children's speech and then adapt those features to the speech of younger children. For infant VC, SSL models pre-trained on large-scale home recordings learn to leverage phonetic representations at middle layers, and thereby enhance the performance of this task.

关键词： Adaptation models Analytical models Speech recognition Self-supervised learning Speech enhancement Phonetics Encoding

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multilingual Communication Enhancement Using Transformer Model for Social Media Platform 15

Real-Time Multilingual Communication Enhancement Using Trans...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Changala, Ravindra Manogna, Jerripothula Geetha, K. Pathak, Punit Dash, Chinmaya Bala, B Kiran Guru Nanak Institutions Technical Campus Department of Information Technology Hyderabad India Duvvada India Jain University Department of English Bangalore India Auro University School of Liberal Arts and Human Sciences Surat India St. Claret College Department of Computer Science Bangalore India K.Ramakrishnan College of Engineering Department of AI & DS Trichy India

ISBN: (纸本)9798350370249

Social media platforms have become integral to global communication, connecting individuals from diverse linguistic backgrounds. However, the language barrier remains a significant challenge, hindering effective cross-cultural interaction. This paper introduces a real-time multilingual communication enhancement system for social media platforms, leveragingBidirectional Encoder Representations from Transformers (BERTs). This approach addresses these drawbacks by employing a pre-trained Transformer model, fine-tuned on a comprehensive dataset curated from the platform itself. The novelty of this system lies in its real-time capabilities and the utilization of cutting-edge Transformer architectures, enabling users to engage in instantaneous multilingual conversations. By integrating this model into the social media platform's infrastructure, they provide a user-friendly interface that allows individuals to select their preferred language, with automatic language detection for incoming messages. They evaluate the system's performance using established metrics, including translation accuracy, response time, and user satisfaction. Continuous monitoring and a feedback loop are implemented to iteratively enhance the model's performance over time. The proposed system represents a significant advancement in overcoming language barriers on social media platforms, fostering a more inclusive and globally connected online community with accuracy 92.3%. Through empirical evaluation and user feedback, they demonstrate the effectiveness and practicality of the approach. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Towards Attention-Based ANN Models for Tabular Data Regression: A Use Case of Water Desalination

Towards Attention-Based ANN Models for Tabular Data Regressi...

引用

International Conference on Communications, Signal Processing, and their Applications (ICCSPA)

作者： Abdallah Ragab Omar Sheta Tamer ElBatt Essam Mohamed Department of Computer Science and Engineering The Centre of Excellence for Water Institute of Global Health and Human Ecology The American University in Cairo New Cairo Egypt

ISBN: (数字)9798350384819

ISBN: (纸本)9798350384826

In this paper, we propose a novel machine learning model applied to water desalination processes as a potential use case. Machine learning models show great promise in diverse fields, unlike model-based, often complex mathematical tools, due to their model-free nature and ability to learn from new data. In particular, we start with a classic artificial neural network (ANN) model and explore the potential of boosting its prediction performance using recently introduced attention-based models. This is among the early work to explore attention models for tabular data regression. Moreover, to the best of the authors' knowledge, it is the first to apply attention-based ANN models for tabular data regression to air gap membrane distillation (AGMD) water desalination processes. To test the merits of our proposed approach and better understand potential tradeoffs, we rely on a public dataset representing AGMD water desalination processes to predict key system parameters. We demonstrate the superior performance of our proposed model compared to a classic ANN-based baseline model in [1], which is attributed primarily to incorporating attention.

关键词： Performance evaluation Atmospheric modeling Air gaps Desalination Artificial neural networks Predictive models Signal processing Mathematical models Data models Feeds

来源：评论

学校读者我要写书评

暂无评论

Domain-Enhanced Attention Enabled Deep Network for Behavioral Health Identification from 911 Narratives

Domain-Enhanced Attention Enabled Deep Network for Behaviora...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Azmee, Abm Adnan Brown, Martin Khan, Md Abdullah Al Hafiz Thomas, Dominic Pei, Yong Nandan, Monica Kennesaw State University Department of Computer Science Marietta United States Kennesaw State University Data Science and Analytics Marietta United States Kennesaw State University Information Systems Marietta United States Kennesaw State University Social Work and Human Services Marietta United States

ISBN: (纸本)9798350324457

Appropriately addressing behavioral health challenges is a problem in the United States. Behavioral health challenges can manifest in the form of crimes committed by individuals with mental illness, social and domestic violence, etc., which may result in emergency calls to first responders. For example, in domestic violence situations, involved parties may need various supports and resources if no criminal charges are filed. In these instances, when a 911 call is made, it mobilizes the entire first responder system (e.g., police, fire, EMT), each of whom write their respective incident reports. A majority of the calls that first responders are addressing are social and behavioral in nature, which they are often ill-equipped to handle. The recurring nature of these calls and limited available resources, first responders encounter challenges in providing appropriate responses to community residents. Therefore, early identification of these cases through incident reports could guide service providers and first responders to take appropriate actions on behalf of the community resident. However, the presence of noise and contextual variability within these unstructured public narrative reports makes it challenging for identifying social and behavioral health based cases. To address this challenge, in this study, we propose a novel model to analyze the first responders' public narratives: the model learns contextual features automatically from the public narratives by employing self-attention techniques and incorporates automatically extracted domain knowledge by comparing expert-given keywords to represent document features to identify behavioral health cases. Unlike conventional approaches, integrating domain expert knowledge with the contextual representation of the public narrative report enriches the model's understanding of social and behavioral health cues and enhances its overall performance. Extensive evaluation showcases the efficacy and effectiveness of our pro

关键词： Behavioral Health Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Segmenting Anything in the Dark via Depth Perception

引用

IEEE Transactions on Multimedia 2025年 27卷 2975-2986页

作者： Liu, Peng Deng, Jinhong Duan, Lixin Li, Wen Lv, Fengmao University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China UESTC Shenzhen Institute for Advanced Study Shenzhen518110 China University of Electronic Science and Technology of China Sichuan Provincial Key Laboratory for Human Disease Gene Study Center for Medical Genetics Department of Laboratory Medicine Sichuan Academy of Medical Sciences Sichuan Provincial People's Hospital Chengdu610032 China Southwest Jiaotong University Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education School of Computing and Artificial Intelligence Chengdu611756 China

Image segmentation under low-light conditions is essential in real-world applications, such as autonomous driving and video surveillance systems. The recent Segment Anything Model (SAM) exhibits strong segmentation capability in various vision applications. However, its performance could be severely degraded under low-light conditions. On the other hand, multimodal information has been exploited to help models construct more comprehensive understanding of scenes under low-light conditions by providing complementary information (e.g., depth). Therefore, in this work, we present a pioneer attempt that elevates a unimodal vision foundation model (e.g., SAM) to a multimodal one, by efficiently integrating additional depth information under low-light conditions. To achieve that, we propose a novel method called Depth Perception SAM (DPSAM) based on the SAM framework. Specifically, we design a modality encoder to extract the depth information and the Depth Perception Layers (DPLs) for mutual feature refinement between RGB and depth features. The DPLs employ the cross-modal attention mechanism to mutually query effective information from both RGB and depth for the subsequent feature refinement. Thus, DPLs can effectively leverage the complementary information from depth to enrich the RGB representations and obtain comprehensive multimodal visual representations for segmenting anything in the dark. To this end, our DPSAM maximally maintains the instinct expertise of SAM for RGB image segmentation and further leverages on the strength of depth for enhanced segmenting anything capability, especially for cases that are likely to fail with RGB only (e.g., low-light or complex textures). As demonstrated by extensive experiments on four RGBD benchmark datasets, DPSAM clearly improves the performance for the segmenting anything performance in the dark, e.g., +12.90% mIoU and +16.23% mIoU on LLRGBD and DeLiVER, respectively. © 1999-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Extending the windows desktop interface with connected handheld computers 4

Extending the windows desktop interface with connected handh...

引用

4th USENIX Windows Systems Symposium

作者： Myers, Brad A. Miller, Robert C. Bostwick, Benjamin Evankovich, Carl Human Computer Interaction Institute School of Computer Science Carnegie Mellon University PittsburghPA15213 United States

Increasingly, people will be in situations where there are multiple communicating computing devices that have input / output capabilities. For example, people might carry their handheld computer, such as a Windows CE device or a Palm Pilot, into a room with a desktop or an embedded computer. The handheld computer can communicate with the PC using wired or wireless technologies, and then both computers can be used at the same time. We are investigating many ways in which the handheld computer can be used to extend the functions of existing and new applications. For example, the handheld's screen can be used as a customizable input and output device, to provide various controls for desktop applications. The handheld can contain scroll bars, buttons, virtual knobs and menus. It can also display the slide notes or a list of slide titles for a presentation, the list of current tasks and windows, and lists of links for web browsing. The user can tap on these lists on the handheld to control the PC. Information and control can flow fluidly among all the user's devices, so that there is an integrated environment. © 2020 *** right reserved.

关键词： Taps

来源：评论

学校读者我要写书评

暂无评论

SLAMSpoof: Practical LiDAR Spoofing Attacks on Localization Systems Guided by Scan Matching Vulnerability Analysis

arXiv

引用

arXiv 2025年

作者： Nagata, Rokuto Koide, Kenji Hayakawa, Yuki Suzuki, Ryo Ikeda, Kazuma Sako, Ozora Chen, Qi Alfred Sato, Takami Yoshioka, Kentaro Department of Electronics and Electrical Engineering Keio University Japan Department of Information Technology and Human Factors the National Institute of Advanced Industrial Science and Technology Japan Department of Computer Science University of California Irvine United States

Accurate localization is essential for enabling modern full self-driving services. These services heavily rely on map-based traffic information to reduce uncertainties in recognizing lane shapes, traffic light locations, and traffic signs. Achieving this level of reliance on map information requires centimeter-level localization accuracy, which is currently only achievable with LiDAR sensors. However, LiDAR is known to be vulnerable to spoofing attacks that emit malicious lasers against LiDAR to overwrite its measurements. Once localization is compromised, the attack could lead the victim off roads or make them ignore traffic lights. Motivated by these serious safety implications, we design SLAMSpoof, the first practical LiDAR spoofing attack on localization systems for self-driving to assess the actual attack significance on autonomous vehicles. SLAMSpoof can effectively find the effective attack location based on our scan matching vulnerability score (SMVS), a point-wise metric representing the potential vulnerability to spoofing attacks. To evaluate the effectiveness of the attack, we conduct real-world experiments on ground vehicles and confirm its high capability in real-world scenarios, inducing position errors of ≥4.2 meters (more than typical lane width) for all 3 popular LiDAR-based localization algorithms. We finally discuss the potential countermeasures of this attack. Code is available at https://***/Keio-CSG/slamspoof © 2025, CC BY.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Towards Robotised Palpation for Cancer Detection through Online Tissue Viscoelastic Characterisation with a Collaborative Robotic Arm

Towards Robotised Palpation for Cancer Detection through Onl...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Luca Beber Edoardo Lamon Giacomo Moretti Daniele Fontanelli Matteo Saveriano Luigi Palopoli Department of Information Engineering and Computer Science Università di Trento Trento Italy DRIM Ph.D. of National Interest in Robotics and Intelligent Machines Human-Robot Interfaces and Interaction Istituto Italiano di Tecnologia Genoa Italy Department of Industrial Engineering Università di Trento Trento Italy

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper introduces a new method for online estimating the penetration of the end-effector and the viscoelastic properties of a soft body, through palpation exams using a collaborative robotic arm. The estimator is based on the dimensionality reduction method that simplifies the nonlinear Hunt-Crossley model. In addition, in our algorithm, the model parameters can be found without a force sensor, leveraging only the robotic arm controller data. An extended Kalman filter is employed to achieve online estimation, which embeds the dynamic contact model. The algorithm is tested with various types of silicone, a material that resembles biological tissues, including samples with hard intrusions to simulate cancerous cells within a softer tissue. The results indicate that this technique can accurately determine the model parameters and estimate the penetration of the end-effector into the soft body. These promising preliminary results demonstrate robots’ potential to be an effective tool for early-stage cancer diagnostics.

关键词： Dimensionality reduction Biological system modeling Heuristic algorithms Biological tissues Estimation Collaboration Robot sensing systems Information filters End effectors Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Behaviour of Tree-Based Neural Networks in Regression Tasks

arXiv

引用

arXiv 2024年

作者： Samoaa, Peter Farahani, Mehrdad Longa, Antonio Leitner, Philipp Chehreghani, Morteza Haghir Data Science and AI Division Chalmers University of Technology Gothenburg Sweden Interaction Design and Software Engineering Division Chalmers University of Technology Gothenburg Sweden Department of Information Engineering and Computer Science University of Trento Trento Italy

The landscape of deep learning has vastly expanded the frontiers of source code analysis, particularly through the utilization of structural representations such as Abstract Syntax Trees (ASTs). While these methodologies have demonstrated effectiveness in classification tasks, their efficacy in regression applications, such as execution time prediction from source code, remains underexplored. This paper endeavours to decode the behaviour of tree-based neural network models in the context of such regression challenges. We extend the application of established models—tree-based Convolutional Neural Networks (CNNs), Code2Vec, and Transformer-based methods—to predict the execution time of source code by parsing it to an AST. Our comparative analysis reveals that while these models are benchmarks in code representation, they exhibit limitations when tasked with regression. To address these deficiencies, we propose a novel dual-transformer approach that operates on both source code tokens and AST representations, employing cross-attention mechanisms to enhance interpretability between the two domains. Furthermore, we explore the adaptation of Graph Neural Networks (GNNs) to this tree-based problem, theorizing the inherent compatibility due to the graphical nature of ASTs. Empirical evaluations on real-world datasets showcase that our dual-transformer model outperforms all other tree-based neural networks and the GNN-based models. Moreover, our proposed dual transformer demonstrates remarkable adaptability and robust performance across diverse datasets. © 2024, CC BY-NC-SA.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Transformer-based direct hidden Markov model for machine translation 59

Transformer-based direct hidden Markov model for machine tra...

引用

2021 Student Research Workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Wang, Weiyue Yang, Zijian Gao, Yingbo Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Germany

ISBN: (纸本)9781954085558

The neural hidden Markov model has been proposed as an alternative to attention mechanism in machine translation with recurrent neural networks. However, since the introduction of the transformer models, its performance has been surpassed. This work proposes to introduce the concept of the hidden Markov model to the transformer architecture, which outperforms the transformer baseline. Interestingly, we find that the zero-order model already provides promising performance, giving it an edge compared to a model with first-order dependency, which performs similarly but is significantly slower in training and decoding. © 2021 Association for Computational Linguistics.

关键词： Hidden Markov models

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：