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： Zeinali, Hossein Lee, Kong Aik Alam, Jahangir Burget, Lukáš Department of Computer Engineering Amirkabir University of Technology Tehran Iran Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Kowloon Hong Kong Department of Computer Graphics and Multimedia Brno University of Technology Brno Czech Republic Computer Research Institute of Montreal Montreal Canada

ISBN: (纸本)9798350368741

In contrast to text-independent speaker verification, which has received significant attention from researchers and has many competitions dedicated to it, text-dependent speaker verification (TdSV) has been less explored recently. The TdSV Challenge 2024 was organized to analyze and explore novel methods for this type of speaker verification and aims to motivate participants to develop new approaches to TdSV, conduct comprehensive analyses, and investigate advanced techniques such as self-supervised learning. This challenge builds on the achievements of the short-duration speaker verification (SdSV) Challenges held in 2020 and 2021 and focuses specifically on TdSV in two distinct scenarios. The first scenario involves conventional TdSV, while the second focuses on speaker enrollment using user-defined passphrases. This paper provides a detailed description of both tasks, introduces the evaluation rules, and presents a comprehensive analysis of the results obtained from this challenge. © 2025 IEEE.

关键词： DeepMine dataset TdSV Challenge Text-dependent Speaker Verification User-defined passphrase

来源：评论

学校读者我要写书评

暂无评论

Text-dependent Speaker Verification Challenge 2024: Exploring Shared and User-defined Passphrases

Text-dependent Speaker Verification Challenge 2024: Explorin...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hossein Zeinali Kong Aik Lee Jahangir Alam Lukáš Burget Department of Computer Engineering Amirkabir University of Technology Tehran Iran Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Kowloon Hong Kong Computer Research Institute of Montreal Montreal Canada Department of Computer Graphics and Multimedia Brno University of Technology Brno Czech Republic

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Self-supervised learning Organizations Signal processing Acoustics Speaker recognition Speech processing

来源：评论

学校读者我要写书评

暂无评论

Prediction of the final size for COVID-19 epidemic using machine learning:A case study of Egypt

引用

Infectious Disease Modelling 2020年第1期5卷 622-634页

作者： Lamiaa A.Amar Ashraf A.Taha Marwa Y.Mohamed Networks and Distributed Systems Department Informatics Research InstituteCity of Scientific Research and Technological ApplicationsSRTA-CITYEgypt Multimedia and Computer Graphics Department Informatics Research InstituteCity of Scientific Research and Technological ApplicationsSRTA-CITYEgypt Department of Mathematics and Computer Science Faculty of ScienceAlexandria UniversityEgypt

COVID-19 is spreading within the sort of an enormous epidemic for the *** epidemic infects a lot of individuals in *** World Health Organization states that COVID-19 could be spread from one person to another at a very fast speed through contact and respiratory *** these days,Egypt and all countries worldwide should rise to an effective step to investigate this disease and eliminate the effects of this *** this paper displayed,the real database of COVID-19 for Egypt has been analysed from February 15,2020,to June 15,2020,and predicted with the number of patients that will be infected with COVID-19,and estimated the epidemic final *** regression analysis models have been applied for data analysis of COVID-19 of *** this study,we’ve been applied seven regression analysis-based models that are exponential polynomial,quadratic,thirddegree,fourth-degree,fifth-degree,sixth-degree,and logit growth respectively for the COVID-19 ***,the exponential,fourth-degree,fifth-degree,and sixth-degree polynomial regression models are excellent models specially fourth-degree model that will help the government preparing their procedures for one *** addition,we have applied the well-known logit growth regression model and we obtained the following epidemiological insights:Firstly,the epidemic peak could possibly reach at 22-June 2020 and final time of epidemic at 8-September ***,the final total size for cases 1.6676Et05 *** action from government of interevent over a relatively long interval is necessary to minimize the final epidemic size.

关键词： COVID-19 Regression analysis model Epidemic model

来源：评论

学校读者我要写书评

暂无评论

PRS-Net: Planar reflective symmetry detection net for 3D models

arXiv

引用

arXiv 2019年

作者： Gao, Lin Zhang, Ling-Xiao Meng, Hsien-Yu Ren, Yi-Hui Lai, Yu-Kun Kobbelt, Leif Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Maryland College ParkMD United States Visual Computing Group School of Computer Science and Informatics Cardiff University Wales United Kingdom Institute for Computer Graphics and Multimedia RWTH Aachen University Aachen Germany

In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

The zero resource speech challenge 2019: TTS without T

arXiv

引用

arXiv 2019年

作者： Dunbar, Ewan Algayres, Robin Karadayi, Julien Bernard, Mathieu Benjumea, Juan Cao, Xuan-Nga Miskic, Lucie Dugrain, Charlotte Ondel, Lucas Black, Alan W. Besacier, Laurent Sakti, Sakriani Dupoux, Emmanuel Laboratoire de Linguistique Formelle CNRS Paris Diderot Sorbonne Paris Cité France Cognitive Machine Learning ENS CNRS EHESS INRIA PSL Research University France Department of Computer Graphics and Multimedia Brno Univ. of Technology Czech Republic Language Technologies Institute Carnegie Mellon University United States Laboratoire d'Informatique de Grenoble GETALP Université Grenoble Alpes France Nara Institute of Science and Technology RIKEN Center for Advanced Intelligence Project Japan Facebook A.I. Research Paris France

We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text). We provide raw audio for a target voice in an unknown language (the Voice dataset), but no alignment, text or labels. Participants must discover subword units in an unsupervised way (using the Unit Discovery dataset) and align them to the voice recordings in a way that works best for the purpose of synthesizing novel utterances from novel speakers, similar to the target speaker's voice. We describe the metrics used for evaluation, a baseline system consisting of unsupervised subword unit discovery plus a standard TTS system, and a topline TTS using gold phoneme transcriptions. We present an overview of the 19 submitted systems from 10 teams and discuss the main results. Copyright © 2019, The Authors. All rights reserved.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Wifbs: A web-based image feature benchmark system 21

Wifbs: A web-based image feature benchmark system

引用

21st International Conference on multimedia Modeling, MMM 2015

作者： Spehr, Marcel Grottel, Sebastian Gumhold, Stefan Chair of Computer Graphics and Visualisation Institute of Software and Multimedia Technology TU Dresden Nöthnitzer Strasse 46 Dresden01087 Germany

ISBN: (纸本)9783319144412

Automatic analysis of image data is of high importance for many applications. Given an image classification problem one needs three things: (i) Training data and tools to extract (ii) relevant visual information— usually image features—that can be used by (iii) classification algorithms. For given (i), a multitude of candidates present themselves for (ii) and (iii). Model selection becomes the main issue. We present a webbased feature benchmark system enabling system designers to streamline tool-chains to specific needs using available implementations of candidate tools. Our system features a modular architecture, remote and parallel computing, extensibility and—from a user’s standpoint—platform independence due to its web-based nature. Using Wifbs1, image features can be subjected to a sophisticated and unbiased model selection procedure to compose optimized pipelines for given image classification problems. © Springer International Publishing Switzerland 2015.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

An optical guiding system for gesture based interactions in smart environments

An optical guiding system for gesture based interactions in ...

引用

2nd International Conference on Distributed, Ambient and Pervasive Interactions, DAPI 2014 - Held as Part of 16th International Conference on Human-computer Interaction, HCI International 2014

作者： Majewski, Martin Dutz, Tim Wichert, Reiner Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Multimedia Communications Lab Technische Universitaet Darmstadt Germany

ISBN: (纸本)9783319077871

Using gestures to control Ambient Intelligence environments can result in mismatches between the user's intention and the perception of the gesture by the system. One way to cope with this problem is to provide the user with an instant feedback on what the system has perceived. In this work, we present an approach for providing visual feedback to users of Ambient Intelligence systems that rely on gestures to control individual devices within their environments. This paper extends our previous work on this topic [1] and introduces several enhancements to the system. © 2014 Springer International Publishing Switzerland.

关键词： Ambient intelligence

来源：评论

学校读者我要写书评

暂无评论

Annotation-based feature extraction from sets of SBML Models

Annotation-based feature extraction from sets of SBML Models

引用

10th International Conference on Data Integration in the Life Sciences, DILS 2014

作者： Alm, Rebekka Waltemath, Dagmar Wolkenauer, Olaf Henkel, Ron Dept. of Multimedia Communication University of Rostock Germany Fraunhofer Institute for Computer Graphics Rostock Germany Dept. of Systems Biology and Bioinformatics University of Rostock Germany Wallenberg Research Centre at Stellenbosch University Stellenbosh South Africa

ISBN: (纸本)9783319085890

Model repositories such as BioModels Database provide computational models of biological systems for the scientific community. These models contain rich semantic annotations that link model entities to concepts in well-established bio-ontologies such as Gene Ontology. Consequently, thematically similar models are likely to share similar annotations. Based on this assumption, we argue that semantic annotations are a suitable tool to characterize sets of models. These characteristics can then help to classify models, to identify additional features for model retrieval tasks, or to enable the comparison of sets of models. In this paper, we present four methods for annotation-based feature extraction from model sets. All methods have been used with four different model sets in SBML format and taken from BioModels Database. To characterize each of these sets, we analyzed and extracted concepts from three frequently used ontologies for SBML models, namely Gene Ontology, ChEBI and SBO. We find that three of the four tested methods are suitable to determine characteristic features for model sets. The selected features vary depending on the underlying model set, and they are also specific to the chosen model set. We show that the identified features map on concepts that are higher up in the hierarchy of the ontologies than the concepts used for model annotations. Our analysis also reveals that the information content of concepts in ontologies and their usage for model annotation do not correlate. © 2014 Springer International Publishing Switzerland.

关键词： Gene Ontology

来源：评论

学校读者我要写书评

暂无评论

Animating turbulent water by vortex shedding in PIC/FLIP

引用

Science China(Information Sciences) 2013年第3期56卷 16-26页

作者： ZHU Jian LIU YouQuan CHANG YuanZhang WU EnHua Computer Graphics and Multimedia Laboratory(NG04) Faculty of Science and TechnologyUniversity of Macau School of Information Engineering Chang'an University State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of Sciences

In this paper,we present a hybrid method,which integrates PIC/FLIP and vortex particle methods into a unified framework,to efficiently simulate vortex shedding that happens when fluids flow around internal *** improve efficiency and reduce the numerical dissipations,we first solve the governing equations on a coarse grid using PIC/FLIP,and then interpolate the intermediate results to a finer grid to obtain the base *** the regular particles in PIC/FLIP enter the boundary layer,if the specified conditions are satisfied to cause vortex shedding,they are selected as vortex particles by assigning additional vorticity related *** vortex particle dynamics are controlled by the vorticity form of NS equations,and several efficient methods are proposed to solve them on the finer ***,the obtained turbulence flow is added to the base *** a result,we are able to simulate turbulent water with rich wake details around the internal obstacles.

关键词： physically based fluid simulation turbulence vortex shedding vortex particle PIC/FLIP

来源：评论

学校读者我要写书评

暂无评论

AmbiTrack - Marker-free Indoor Localization and Tracking of Multiple Users in Smart Environments with a Camera-based Approach

AmbiTrack - Marker-free Indoor Localization and Tracking of ...

引用

International Competitions and Final Workshop, EvAAL 2013

作者： Braun, Andreas Dutz, Tim Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany KOM - Multimedia Communications Lab TU Darmstadt Darmstadt Germany

ISBN: (纸本)9783642410420

Systems providing tracking and localization of persons in an indoor environment have been continuously proposed in recent years, particularly for Pervasive Computing applications. AmbiTrack is a system that provides marker-free localization and tracking, i.e., it does not require the users to carry any tag with them in order to perform localization. This allows easy application in circumstances where wearing a tag is not viable, e.g. in typical Ambient Assisted Living scenarios, where users may not be well-versed technologically. In this work, we present the AmbiTrack system and its adaptation for the EvAAL competition 2013. We present a marker-free, camera-based system for usage in indoor environments designed for cost-effectiveness and reliability. We adapt our previously presented system to make it more reliable in tracking multiple persons, using context information for improving recognition rate and simplifying the installation. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Cost effectiveness

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：