检索结果-内蒙古大学图书馆

The Database and Benchmark For the Source Speaker Tracing Challenge 2024

学校读者我要写书评

暂无评论

The Database and Benchmark For the Source Speaker Tracing Ch...

IEEE Spoken Language Technology Workshop

作者： Ze Li Yuke Lin Tian Yao Hongbin Suo Pengyuan Zhang Yanzhen Ren Zexin Cai Hiromitsu Nishizaki Ming Li School of Computer Science Wuhan University Wuhan China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan China AI Center OPPO Beijing China Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics CAS China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Center for Language and Speech Processing Johns Hopkins University USA Integrated Graduate School of Medicine Engineering and Agricultural Sciences University of Yamanashi 4-4-37 Takeda Kofu Yamanashi Japan

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Voice conversion (VC) systems can transform audio to mimic another speaker’s voice, thereby attacking speaker verification (SV) systems. However, ongoing studies on source speaker verification (SSV) are hindered by limited data availability and methodological constraints. This paper presents the Source Speaker Tracking Challenge (SSTC) on STL 2024, which aims to fill the gap in the database and benchmark for the SSV task. In this study, we generate a large-scale converted speech database with 16 common VC methods and train a batch of baseline systems based on the MFA-Conformer architecture. In addition, we introduced a related task called conversion method recognition, with the aim of assisting the SSV task. We expect SSTC to be a platform for advancing the development of the SSV task and provide further insights into the performance and limitations of current SV systems against VC attacks. Further details about SSTC can be found here 1 . 1 https://***/

关键词： Databases Conferences Transforms Contrastive learning Benchmark testing Multitasking Calibration

AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Forged content shared widely on social media platforms is a major social problem that requires increased regulation and poses new challenges to the research community. The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous work on detecting AI-generated fake videos only utilizes visual modality or audio modality. While there are some methods in the literature that exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multi-modal datasets of deepfake videos involving acoustic and visual manipulations. Moreover, these existing methods are mostly based on CNN and suffer from low detection accuracy. Inspired by the recent success of Transformer in various fields, to address the challenges posed by deepfake technology, in this paper, we propose an Audio-Visual Transformer-based Ensemble Network (AVTENet) framework that considers both acoustic manipulation and visual manipulation to achieve effective video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multi-modal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that our best model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. © 2023, CC BY.

关键词： Statistical tests

Decoherence on staggered quantum walks

学校读者我要写书评

暂无评论

Physical Review A 2022年第3期105卷 032452-032452页

作者： Raqueline A. M. Santos Franklin de L. Marquezino Center for Quantum Computer Science Faculty of Computing University of Latvia Raina bulvaris 19 Riga LV-1586 Latvia Systems Engineering and Computer Science Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering Federal University of Rio de Janeiro Avenida Horacio Macedo 2030 H319 Rio de Janeiro 21941-972 Brazil Multidisciplinary Laboratory for Research in Computer Science Federal University of Rio de Janeiro Rodovia Washington Luiz 19593 Duque de Caxias 25240-005 Brazil

The decoherence phenomenon has been widely studied in different types of quantum walks. In this work we show how to model decoherence inspired by percolation on staggered quantum walks. Two models of unitary noise are described: breaking polygons and breaking vertices. The evolution operators subject to these noises are obtained, and the equivalence to the coined quantum walk model is presented. Further, we numerically analyze the effect of these decoherence models on the two-dimensional grid of 4-cliques. We examine how these perturbations affect the quantum walk based search algorithm in this graph and how expanding the tessellation intersection can make it more robust against decoherence.

关键词： Network searches Quantum algorithms Quantum computation Quantum information processing Quantum walks

Learning Cyclotron: An Ecosystem of Knowledge Circulation

学校读者我要写书评

暂无评论

Learning Cyclotron: An Ecosystem of Knowledge Circulation

Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous computing and the 2022 ACM International Symposium on Wearable Computers

作者： Andrew Vargo Motoi Iwata Mathilde Hutin Sofiya Kobylyanskaya Ioana Vasilescu Olivier Augereau Ko Watanabe Shoya Ishimaru Benjamin Tag Tilman Dingler Koichi Kise Laurence Devillers Andreas Dengel Graduate School of Informatics Osaka Metropolitan University Japan Osaka Metropolitan University Japan LISN France LISN-CNRS France CNRS Laboratoire Interdisciplinaire des Sciences du Numérique (LISN) Paris-Saclay University France Lab-STICC research laboratory and ENIB France Technische Universität Kaiserslautern Germany University of Kaiserslautern Germany and German Research Center for Artificial Intelligence (DFKI) Germany School of Computing and Information Systems University of Melbourne Australia Smart Data & Knowledge Services German Research Center for Artificial Intelligence Germany

ISBN: (纸本)9781450394239

The circulation of knowledge is an important function for enriching our social life. Knowledge circulation, which has traditionally been conducted manually, is undergoing a transformation in the age of artificial intelligence. In this paper, we describe our project called “Learning Cyclotron (LeCycl),” which was initiated to accelerate the circulation of knowledge for building a knowledge ecosystem based on artificial intelligence technology. The three functions of sensing, mastering, and transferring knowledge are effectively operated through the power of AI-empowered digital nudging strategies. We outline what has been accomplished to date and summarize future directions for the ultimate goal of LeCycl.

关键词： Human learning Knowledge Circulation Intelligence Augmentation Nudge

Exploring the integration of multi criteria decision analysis in the clean energy biodiesels applications: A systematic review and gap analysis

学校读者我要写书评

暂无评论

Engineering Applications of Artificial Intelligence 2024年 133卷

作者： Alamoodi, A.H. Garfan, Salem Al-Zuhairi, Omar Zaidan, B.B. Zaidan, A.A. Albahri, O.S. Y.Y. Ahmaro, Ibraheem Albahri, A.S. Yussof, Salman Magableh, Aws A. Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Malaysia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Perak Malaysia Applied Science Research Center Applied Science Private University Amman Jordan Low Dimensional Materials Research Centre Department of Physics Faculty of Science Universiti Malaya Kuala Lumpur50603 Malaysia SP Jain School of Global Management Lidcombe SydneyNSW2141 Australia International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Victorian Institute of Technology Australia Computer Techniques Engineering Department Mazaya University College Nasiriyah Iraq Computer Science Department College of Information Technology Hebron University Hebron Palestine Technical College Imam Ja'afar Al-Sadiq University Baghdad Iraq Department of Information Systems Yarmouk University Irbid Jordan Baghdad Iraq Department of Computing College of Computing and Informatics Universiti Tenaga Nasional Malaysia Departments of Software Engineering Prince Sultan University Riyad Saudi Arabia

Biodiesel has gained tremendous attention from researchers due to its environmentally friendly and renewable fuel manufactured domestically from vegetable oils or animal fats. Multiple factors, including emission and fuel efficiency, measure the performance of biodiesel. These characteristics make the process of evaluation and benchmarking a multi-criteria decision-making (MCDM) problem. This research attempts to survey the literature for multi-criteria decision-making applications on biodiesel. This systematic review was carried out on four scientific databases: PubMed, ScienceDirect, IEEE Xplore, and WoS. The collected articles were summarized and mapped into a coherent taxonomy, while the main challenges, motivations, and recommendations were collected and categorized for better understanding and finding out essential characteristics. The final set of included articles was 33, and they were categorized into six different categories. Most articles (n=15/33) investigated the evaluation and selection of biodiesel alternatives using MCDM. Furthermore, a state-of-art bibliometric analysis is provided. The analysis demonstrates several challenges in this area, such as source selection, optimum fuel blending, and uncertainty. This article is expected to assist future researchers in addressing the current gaps and contribute to advancing this area. © 2024 Elsevier Ltd

关键词： Biodiesel

THE DATABASE AND BENCHMARK FOR THE SOURCE SPEAKER TRACING CHALLENGE 2024

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Ze Lin, Yuke Yao, Tian Suo, Hongbin Zhang, Pengyuan Ren, Yanzhen Cai, Zexin Nishizaki, Hiromitsu Li, Ming School of Computer Science Wuhan University Wuhan China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan China AI Center OPPO Beijing China Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics CAS China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Center for Language and Speech Processing Johns Hopkins University United States Integrated Graduate School of Medicine Engineering and Agricultural Sciences University of Yamanashi 4-4-37 Takeda Yamanashi Kofu400-8510 Japan

关键词： Database systems

Learning Pairwise Preferences from Movie Ratings

学校读者我要写书评

暂无评论

Learning Pairwise Preferences from Movie Ratings

International Conference on ICT For Smart Society (ICISS)

作者： Nunung Nurul Qomariyah Ahmad Nurul Fajar Faculty of Computing and Media Bina Nusantara University Jakarta Indonesia BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781665404228

ISBN: (纸本)9781665404235

Preference Elicitation is now considered a crucial stage in recommender system. That is the stage where we collect and query preferences of the users as part of interactive decision support system. Preference elicitation can be performed using many ways, such as asking the user explicitly to give ratings or feedbacks for some products, or implicitly observing their behaviour. Once this preference has been collected by the system, it can then be used to generate item recommendation. Using explicit feedback itself, such as rating only, has several drawbacks. Using ratings is very subjective. Two users with similar taste might give different rating to the same item. A user also may not be consistent in giving number to express their liking. In other case, a user may like an item more than the other items, but feels difficult to give lower rating on the other item, because it means that the particular item is just as bad as the one he/she does not like. By showing two different items as a pair, it will be easier for the users to pick which one is the best. In this paper, we show the result of our experiment in predicting user pairwise preferences by using their movie ratings data. We evaluated five different machine learning algorithms to predict the data in pairwise preference format. The result shows that K-Nearest Neighbour and Random Forest outperformed the other algorithms.

关键词： Motion pictures Predictive models Recommender systems Social networking (online) Industries Encoding Task analysis

Drum-aware ensemble architecture for improved joint musical beat and downbeat tracking

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chiu, Ching-Yu Su, Alvin Wen-Yu Yang, Yi-Hsuan The Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan The Department of Computer Science and Information Engineering National Cheng Kung University Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan

This paper presents a novel system architecture that integrates blind source separation with joint beat and downbeat tracking in musical audio signals. The source separation module segregates the percussive and non-percussive components of the input signal, over which beat and downbeat tracking are performed separately and then the results are aggregated with a learnable fusion mechanism. This way, the system can adaptively determine how much the tracking result for an input signal should depend on the input's percussive or non-percussive components. Evaluation on four testing sets that feature different levels of presence of drum sounds shows that the new architecture consistently outperforms the widely-adopted baseline architecture that does not employ source separation. Copyright © 2021, The Authors. All rights reserved.

关键词： Blind source separation

Comparative study of decoding the surface code using simulated annealing under depolarizing noise

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Takeuchi, Yusaku Takada, Yugo Sakashita, Tatsuya Fujisaki, Jun Oshima, Hirotaka Sato, Shintaro Fujii, Keisuke Division of Advanced Electronics and Optical Science Department of Systems Innovation Graduate School of Engineering Science Osaka University Japan Graduate School of Engineering Science Osaka University 1-3 Machikaneyama Toyonaka Osaka560-8531 Japan Center for Quantum Information and Quantum Biology Osaka University Osaka560-0043 Japan Quantum Laboratory Fujitsu Research Fujitsu Limited 4-1-1 Kawasaki Kanagawa211-8588 Japan Fujitsu Quantum Computing Joint Research Division Center for Quantum Information and Quantum Biology Osaka University 1-2 Machikaneyama Toyonaka Osaka565-8531 Japan Center for Quantum Information and Quantum Biology Osaka University 560-0043 Japan Saitama Wako351-0198 Japan

We explored decoding methods for the surface code under depolarizing noise by mapping the problem into the Ising model optimization. We consider two kinds of mapping with and without a soft constraint and also various optimization solvers, including simulated annealing implemented on a CPU,"Fujitsu Digital Annealer" (DA), a hardware architecture specialized for the Ising problems, and CPLEX, an exact integer programming solver. We find that the proposed Ising-based decoding approaches provide higher accuracy compared to the minimum-weight perfect matching (MWPM) algorithm for depolarizing noise and comparable to minimum distance decoding using CPLEX. While decoding time is longer than MWPM when we compare it with a single core CPU, our method is amenable to parallelization and easy to implement on dedicated hardware, suggesting potential future speedups. Regarding the mapping methods to the Ising model with and without a soft constraint, the SA decoder yielded higher accuracy without a soft constraint. In contrast, the DA decoder shows less difference between the two mapping methods, which indicates that DA can find a better solution with smaller number of iterations even under the soft constraint. Our results are important for devising efficient and fast decoders feasible with quantum computer control devices. Copyright © 2023, The Authors. All rights reserved.

关键词： Simulated annealing