检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Wei Zhao, Siyi Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

Recent advancements in speech enhancement (SE) techniques have greatly improved speech clarity and intelligibility in challenging acoustic environments. However, integrating SE into automatic speech recognition (ASR) systems often results in performance degradation due to artifacts introduced during the enhancement process. While various methods have enhanced recognition accuracy in SE-ASR systems, they often require fine-tuning or re-training of SE or ASR models, which is impractical in many real-world applications. In this paper, we propose a lightweight distortion suppression (DS) network that addresses these artifacts without modifying the SE or ASR models, treating them as fixed black boxes. The DS module operates on the time-frequency (T-F) bands of the original and enhanced complex spectrograms, efficiently compensating for SE distortions using the original T-F information. We validate our approach through experiments on both Mandarin and English ASR tasks using monaural and multi-channel SE frontends, across various ASR backends. Results show that the DS module significantly improves the performance of SE-ASR systems, even when used with robust commercial ASR backends. © 2025 IEEE.

关键词： non-intrusive robust speech recognition speech distortion speech enhancement

来源：评论

学校读者我要写书评

暂无评论

An Interpretable CNN for the Segmentation of the Left Ventricle in Cardiac MRI by Real-Time Visualization

引用

computer Modeling in Engineering & sciences 2023年第5期135卷 1571-1587页

作者： Jun Liu Geng Yuan Changdi Yang Houbing Song Liang Luo Robotics Institute School of Computer ScienceCarnegie Mellon UniversityPittsburghPA15217USA Department of Electrical&Computer Engineering College of EngineeringNortheastern UniversityBostonMA02115USA Security and Optimization for Networked Globe Laboratory(SONG Lab) Embry-Riddle Aeronautical UniversityDaytona BeachFL32114USA School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu610054China

The interpretability of deep learning models has emerged as a compelling area in artificial intelligence *** safety criteria for medical imaging are highly stringent,and models are required for an ***,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and ***,the interpretability of CNNs has come into the *** medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning ***,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these *** this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac *** enhanced GPU training system implemented interpretable global average pooling for graphics using deep *** deep learning tasks were *** included data management,neural network architecture,and *** system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment *** results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning *** model is lightweight and more convenient to deploy on mobile devices than transfer learning models.

关键词： Interpretable graphics training visualization image segmentation left ventricle CNNs global average pooling

来源：评论

学校读者我要写书评

暂无评论

A Soft Robot Inverse Kinematics for Virtual Reality

A Soft Robot Inverse Kinematics for Virtual Reality

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： James M. Bern William C. May Austin Osborn Francesco Stella Sadra Zargarzadeh Josie Hughes Computer Science Department Williams College Computational Robot Design & Fabrication Lab EPFL Department of Cognitive Robotics Delft University of Technology Delft The Netherlands

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We show how a variety of techniques from computer Graphics can be leveraged to intuitively control the shape (configuration) of arbitrary 3D Soft Robots in VR. Our pipeline, Virtual Reality Soft Robot Inverse Kinematics (VR-Soft IK), overcomes fundamental limitations of general-purpose drag-and-drop soft robot control interfaces by leaving the 2D computer screen for 3D Virtual Reality (VR). VR-Soft IK uses a simulation based on the Finite Element Method (FEM) and a control method based on sensitivity analysis. Additionally, we show that our general control pipeline can be fused with techniques from 3D character animation to skin our simulation with a high-resolution surface mesh, pointing a way toward Mixed Reality Soft Robots. This full Skinned VR-Soft IK pipeline uses skeletal animation and GPU picking. We demonstrate the utility of our pipeline by doing real-time, open-loop control of the real-world 3D soft robotic arm Helix.

关键词： Three-dimensional displays Pipelines Mixed reality Virtual reality Kinematics Soft robotics Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Character Modelling with Sketches and ODE-Based Shape Creation

引用

Numerical Mathematics(Theory,Methods and Applications) 2023年第3期16卷 720-751页

作者： Ouwen Li Haibin Fu Shaojun Bian Xiaosong Yang Xiaogang Jin Andres Iglesias Algirdas Noreika Lihua You Jian Jun Zhang National Centre for Computer Animation Bournemouth UniversityUnited Kingdom State Key Lab of CAD&CG Zhejiang UniversityChina Department of Applied Mathematics and Computational Sciences University of CantabriaSpain Department of Information Science Toho UniversityJapan Indeform Ltd Lithuania

Character models have enormous applications in *** creation of detailed character models is an important *** paper proposes a new and easy-to-use technique to quickly create detailed character models from *** proposed technique consists of two main components:primitive deformer and shape *** this technique,2D silhouette contours of a character model are drawn or extracted from an image or ***,proper geometric primitives are selected and aligned with the corresponding 2D silhouette *** that,a primitive deformer is used to create a base mesh and three shape generators are used to add 3D details to the base *** primitive deformer and three shape generators are developed from ODE-driven *** primitive deformer deforms the aligned geometric primitives to exactly match the 2D silhouette contours in one view plane and obtains a base mesh of a character model consisting of deformed *** shape generators are used to add 3D details to the base mesh by creating local 3D *** experimental results demonstrate that the new technique can quickly create detailed 3D character models from sketches with few manual *** new technique is physics-based and easy to learn and use.

关键词： Sketch-based character modelling shape generators ordinary differential equations finite difference solution

来源：评论

学校读者我要写书评

暂无评论

Retrospective of Kazakh-Russian Sign Language Corpus Formation 11

Retrospective of Kazakh-Russian Sign Language Corpus Formati...

引用

11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources, sign-lang@LREC-COLING 2024

作者： Imashev, Alfarabi Kydyrbekova, Aigerim Mukushev, Medet Sandygulova, Anara Islam, Shynggys Israilov, Khassan Makazhanov, Aibek Yessenbayev, Zhandos Department of Robotics Engineering Nazarbayev University Kazakhstan Computer Science Lab National Laboratory Astana Nazarbayev University Kazakhstan Public Association "Kazakh Deaf Society" Astana Branch Kazakhstan

ISBN: (纸本)9782493814302

Sign language (SL) is a mode of communication that, in most cases, relies on visual perception exclusively and uses the visual-gestural modality. The advent of machine learning techniques has expanded the range of potential applications, not only in industry but also in addressing societal needs. Previous research has already demonstrated encouraging outcomes in developing sign language recognition systems that are both quite accurate and resilient. Nevertheless, the effectiveness and use of algorithms are impacted not only by their accessibility but also, at times to a greater extent, by the presence of substantial quantities of pertinent data. At the start of the local sign language corpus collection in 2015, there was a notable deficit of local Kazakh-Russian Sign Language data available for computer vision and machine-learning tasks. There were already corpora of another lexically close language, Russian Sign Language, but they were aimed at and tailored for lingustic research. We initiated the procedure by collecting data appropriate for machine-learning purposes. The subsets have been incorporated into the principal corpus and will be subject to future enhancements and refinements. This paper provides an overview of the collected components of the Kazakh-Russian Sign Language Corpus and the resulting outcomes derived from them. © 2024 ELRA Language Resources Association: CC BY-NC 4.0.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Needle Manipulation Controller Subject to Uncertainty of Tip Pose Feedback: a Simulation Study

Evaluation of Needle Manipulation Controller Subject to Unce...

引用

International Symposium on Medical robotics (ISMR)

作者： Junling Mei Chang Chang Yanzhou Wang Simon Leonard Iulian Iordachita Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Mechanical Engineering Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Computer Science Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA

ISBN: (数字)9798331599003

ISBN: (纸本)9798331599010

In this paper, we evaluate the performance of our controller for flexible needle manipulation for percutaneous interventions in a finite element (FE) simulator. We investigate the use of electromagnetic (EM) tracking as needle tip pose feedback, and how artificial sensor noises can affect tracking performance of the controller. In our simulated study, the control system shows high targeting accuracy and robustness with an overall tip position error of 0.49 mm. The addition of needle tip orientation feedback further improves the targeting accuracy for deeper targets, with average error of 0.81 mm when only using position feedback, and 0.55 mm when using additional orientation feedback.

关键词： Target tracking Accuracy Uncertainty Medical robotics Noise Needles Robot sensing systems Robustness Finite element analysis Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Choice of Optimal Voltage for DC Power Distribution Systems on More Electric Aircraft

Choice of Optimal Voltage for DC Power Distribution Systems ...

引用

2024 Energy Conversion Congress and Expo Europe, ECCE Europe 2024

作者： Wang, Xin Atkin, Jason Yeoh, Seang Shen Bozhko, Serhiy University of Nottingham Faculty of Engineering The Department of Electrical and Electronic Engineering Nottingham United Kingdom University of Nottingham Computational Optimisation and Learning Lab School of Computer Science Nottingham United Kingdom

ISBN: (纸本)9798350364446

The new generation of aircraft will experience increasing electrical power demands because of the more electric trends and advances in recent years. Adopting higher voltage levels is widely discussed for More Electric Aircraft (MEA) Power Distribution Systems (PDSs) to efficiently deliver the increased power ratings and reduce the system weight. However, higher voltage levels also indicate the risk of electrical insulation failures. Hence, it is essential to select optimised voltage levels for onboard PDSs considering the trade-offs. In addition, the relationship between the PDS weight/efficiency and voltage levels is complex rather than linear, resulting in infeasibility issues when optimising voltage levels. This study proposes a voltage optimisation method based on selecting among a set of components, i.e., converters and cables, for onboard DC PDSs. Moreover, to improve feasibility, the Integrated Converter Component (ICC) concept is proposed to combine each converter with its lightest input/output cables as an integrated block. Hence, the optimal bus voltages can be decided by selecting the lightest and most efficient ICCs while meeting the power delivery and voltage conversion requirements. © 2024 IEEE.

关键词： Bus voltage DC power distribution integrated converter component more electric aircraft optimisation

来源：评论

学校读者我要写书评

暂无评论

Automatic search for photoacoustic marker using automated transrectal ultrasound

引用

Biomedical Optics Express 2023年第11期14卷 6016-6030页

作者： Wu, Zijian Moradi, Hamid Yang, Shuojue Song, Hyunwoo Boctor, Emad M. Salcudean, Septimiu E. Johns Hopkins University Laboratory for Computational Sensing and Robotics BaltimoreMD United States University of British Columbia Dept. of Electrical and Computer Engineering VancouverBC Canada University of Texas at Austin Walker Department of Mechanical Engineering AustinTX United States Johns Hopkins University Dept. of Computer Science BaltimoreMD United States

Real-time transrectal ultrasound (TRUS) image guidance during robot-assisted laparoscopic radical prostatectomy has the potential to enhance surgery outcomes. Whether conventional or photoacoustic TRUS is used, the robotic system and the TRUS must be registered to each other. Accurate registration can be performed using photoacoustic (PA markers). However, this requires a manual search by an assistant [IEEE Robot. Autom. Lett 8, 1287 (2023).]. This paper introduces the first automatic search for PA markers using a transrectal ultrasound robot. This effectively reduces the challenges associated with the da Vinci-TRUS registration. This paper investigated the performance of three search algorithms in simulation and experiment: Weighted Average (WA), Golden Section Search (GSS), and Ternary Search (TS). For validation, a surgical prostate scenario was mimicked and various ex vivo tissues were tested. As a result, the WA algorithm can achieve 0.53°±0.30° average error after 9 data acquisitions, while the TS and GSS algorithm can achieve 0.29◦±0.31◦ and 0.48°±0.32° average errors after 28 data acquisitions. © 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Know-Thy-Basis: Decomposing F26 for Lightweight S-box Implementation

IACR Transactions on Cryptographic Hardware and Embedded Sys...

引用

IACR Transactions on Cryptographic Hardware and Embedded Systems 2024年第4期2024卷 763-794页

作者： Sau, Dilip Sarkar, Sumanta Saha, Dhiman Mandal, Kalikinkar Center for Computational & Data Sciences Indian Institute of Technology Kharagpur India University of Warwick Coventry United Kingdom de.ci.phe.red Lab Department of Computer Science and Engineering Indian Institute of Technology Bhilai India University of New Brunswick FrederictonNB Canada

A recent trend has shown constructions of 6-bit S-boxes that are mostly focused on their cryptographic elegance, while their lightweight aspects have not really been addressed well. This paper attempts to plug-in this existing research gap where we show how the composite structure of the extension field F26 could be leveraged. An earlier well-known example is an efficient implementation of AES S-box using the tower field extension of F28. The case of F2ab is completely different from any tower field as the implementation varies as per the choice of extension – for instance, F(2a)b or F(2b)a, where a and b are prime. Thus, it makes the implementation of S-boxes over F26 = F2(2×3) very interesting. In this work, we systematically study the composite field structure of F26 from a hardware standpoint for a class of S-boxes that are power mapping or their affine equivalents. We analyze the hardware efficiency with respect to different representations of the field extension, i.e., F(22)3or F(23)2. Furthermore, for each extension, we investigate the impact of various choices of bases – for instance, we present the evidence of the effect that normal or polynomial bases have on the implementation. This gives us further insight on the choice of basis with respect to the field extension. In the process, we present a special normal basis, when used in conjunction with F(23)2 results in the least (or very close to least) area in terms of GE for the 18 (6 quadratic and 12 cubic) S-boxes studied in this work. The special normal basis reported here has some algebraic properties which make it inherently hardware friendly and allow us to predict the area reduction, without running a tool. Overall, this work constitutes an extensive hardware characterization of a class of cryptographically significant 6-bit S-boxes giving us interesting insights into the systematic lightweight implementation of S-boxes without relying on an automated tool. © 2024, Ruhr-University of Bochum. All rights

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Hand Gesture Control for Swarm Quadrotor using Wearable Device in Indoor Environments

Low-Cost Hand Gesture Control for Swarm Quadrotor using Wear...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Muhammad Luthfi Harwidjaya Aufaclav Zatu Kusuma Frisky Bilqis Hafsah Ababiel Adhiwirya Panyananda Suryadi Alfahri Rifki Fahrezi Bambang Nurcahyo Prastowo Department of Computer Science and Electronics Embedded System and Robotics Lab UGM Indonesia

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

The control device for quadrotor aerial vehicles has garnered considerable attention in development endeavors aimed at enhancing user interface and interaction in indoor environments. Quadrotor control mechanisms rely on sophisticated remote transmitters, which often come at a substantial cost and necessitate a proficient skill set for operation to adjust in limited space. Consequently, an innovative paradigm to harness wearable technology as a means of controlling multi-drone systems, thereby streamlining user engagement. This novel approach harnesses 2.4 GHz radio frequency communication and leverages hand gestures as a conduit for motion inputs, which are subsequently processed via a machine learning algorithm augmented by a 9 axis Inertial Measurement Unit (IMU) sensor suite. The primary objective of this system pertains to the effective control of multi drones in the context of obstacle avoidance missions in indoor space. As such, this system embodies considerable promise as an alternative avenue for multi-drone system control, characterized by its intuitive nature and enhanced user accessibility.

关键词： Space missions Simulation Aerospace electronics User interfaces Control systems Indoor environment Wearable devices

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：