检索结果-内蒙古大学图书馆

学校读者我要写书评

暂无评论

China CDC weekly 2022年第40期4卷 885-889,I0002-I0005页

作者： Yuan Bai Mingda Xu Caifen Liu Mingwang Shen Lin Wang Linwei Tian Suoyi Tan Lei Zhang Petter Holme Xin Lu Eric H.Y.Lau Benjamin J.Cowling Zhanwei Du WHO Collaborating Centre for Infectious Disease Epidemiology and Control School of Public HealthLi Ka Shing Faculty of MedicineThe University of Hong KongHong Kong Special Administrative RegionChina Laboratory of Data Discovery for Health Limited(D24H) Hong Kong Science ParkHong Kong Special Administrative RegionChina China-Australia Joint Research Center for Infectious Diseases School of Public HealthXi’an Jiaotong University Health Science CenterXi’an CityShaanxi ProvinceChina Department of Genetics University of CambridgeCambridge CB23EHUK College of Systems Engineering National University of Defense TechnologyChangsha CityHunan ProvinceChina Department of Computer Science Aalto UniversityEspooFinland Center for Computational Social Science Kobe UniversityKobeJapan

Introduction:Minimizing the importation and exportation risks of coronavirus disease 2019(COVID-19)is a primary concern for sustaining the“Dynamic COVID-zero”strategy in *** estimation is essential for cities to conduct before relaxing border control ***:Informed by the daily number of passengers traveling between 367 prefectures(cities)in China,this study used a stochastic metapopulation model parameterized with COVID-19 epidemic characteristics to estimate the importation and exportation ***:Under the transmission scenario(R0=5.49),this study estimated the cumulative case incidence of Changchun City,Jilin Province as 3,233(95%confidence interval:1,480,4,986)before a lockdown on March 14,2022,which is close to the 3,168 cases reported in real life by March 16,*** a total of 367 prefectures(cities),127(35%)had high exportation risks according to the simulation and could transmit the disease to 50%of all other regions within a period from 17 to 94 *** average time until a new infection arrives in a location in 1 of the 367 prefectures(cities)ranged from 26 to 101 ***:Estimating COVID-19 importation and exportation risks is necessary for preparedness,prevention,and control measures of COVID-19—especially when new variants emerge.

关键词： Export Changchun prevention

DISENTANGLING THE PROSODY AND SEMANTIC INFORMATION WITH PRE-TRAINED MODEL FOR IN-CONTEXT LEARNING BASED ZERO-SHOT VOICE CONVERSION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Zhengyang Wang, Shuai Zhang, Mingyang Liu, Xuechen Yamagishi, Junichi 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 Shenzhen Research Institute of Big Data Shenzhen China Chinese University of Hong Kong Shenzhen China National Institute of Informatics Tokyo Japan

Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic tokens, our experiments on the LibriTTS dataset demonstrate that ICL-VC improves speaker similarity. Additionally, we find that k-means is a versatile tokenization method applicable to various pre-trained models. However, the ICL-VC system faces challenges in preserving the prosody of the source speech. To mitigate this issue, we propose incorporating prosody embeddings extracted from a pre-trained emotion recognition model into our system. Integration of prosody embeddings notably enhances the system's capability to preserve source speech prosody, as validated on the Emotional Speech database. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Disentangling The Prosody And Semantic Information With Pre-Trained Model For In-Context Learning Based Zero-Shot Voice Conversion

学校读者我要写书评

暂无评论

Disentangling The Prosody And Semantic Information With Pre-...

IEEE Spoken Language Technology Workshop

作者： Zhengyang Chen Shuai Wang Mingyang Zhang Xuechen Liu Junichi Yamagishi Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China Chinese University of Hong Kong Shenzhen China National Institute of Informatics Tokyo Japan

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Voice conversion (VC) aims to modify the speaker’s timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic tokens, our experiments on the LibriTTS dataset demonstrate that ICL-VC improves speaker similarity. Additionally, we find that k-means is a versatile tokenization method applicable to various pre-trained models. However, the ICL-VC system faces challenges in preserving the prosody of the source speech. To mitigate this issue, we propose incorporating prosody embeddings extracted from a pre-trained emotion recognition model into our system. Integration of prosody embeddings notably enhances the system’s capability to preserve source speech prosody, as validated on the Emotional Speech database.

关键词： Training Emotion recognition databases Semantics Self-supervised learning Speech enhancement Tokenization Text to speech Multilingual Timbre

Pretraining and the Lasso

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Craig, Erin Pilanci, Mert Le Menestrel, Thomas Narasimhan, Balasubramanian Rivas, Manuel A. Gullaksen, Stein-Erik Dehghannasiri, Roozbeh Salzman, Julia Taylor, Jonathan Tibshirani, Robert Department of Biomedical Data Science Stanford University Stanford CA United States Department of Electrical Engineering Stanford University Stanford CA United States Institute for Computational and Mathematical Engineering Stanford University Stanford CA United States Department of Statistics Stanford University Stanford CA United States Department of Biochemistry Stanford University Stanford CA United States Department of Medicine Hematology Section Haukeland University Hospital Bergen Norway K.G. Jebsen Centre for Myeloid Blood Cancer Department of Clinical Science University of Bergen Bergen Norway

Pretraining is a popular and powerful paradigm in machine learning to pass information from one model to another. As an example, suppose one has a modest-sized dataset of images of cats and dogs, and plans to fit a deep neural network to classify them from the pixel features. With pretraining, we start with a neural network trained on a large corpus of images, consisting of not just cats and dogs but hundreds of other image types. Then we fix all of the network weights except for the top layer(s) (which makes the final classification) and train (or "fine tune") those weights on our dataset. This often results in dramatically better performance than the network trained solely on our smaller dataset. In this paper, we ask the question "Can pretraining help the lasso?". We develop a framework for the lasso in which a model is fit to a large dataset, and then fine-tuned using a smaller dataset. This latter dataset can be a subset of the original dataset, or it can be a dataset with a different but related outcome. This framework has a wide variety of applications, including stratified models, multinomial responses, multi-response models, conditional average treatment estimation and even gradient boosting. In the stratified model setting, the pretrained lasso pipeline estimates the coefficients common to all groups at the first stage, and then group-specific coefficients at the second "fine-tuning" stage. We show that under appropriate assumptions, the support recovery rate of the common coefficients is superior to that of the usual lasso trained only on individual groups. This separate identification of common and individual coefficients can also be useful for scientific understanding. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Analysis of Panoramic Images using Deep Learning For Dental Disease Identification

学校读者我要写书评

暂无评论

Analysis of Panoramic Images using Deep Learning For Dental ...

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Mohamed Mallick Midhun Kumar A Sakthi Govindaraju A. Suresh Kumar Manivel Kandasamy P Anitha Rathinam Group of Institutions Coimbaotore Database Engineer Indian Biological Data Center Center for Biotechnology Faridabab School of Computing Science and Engineering Galogotias University Delhi NCR Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Unitedworld School of Computational Intelligence Karnavati University Gujarat India OASYS Institute of Technology Trichy India

Dental caries is a distinct disease strategy caused by the metabolic action of dental biofilm, which continually demineralizes lacquer and dentine. Its commonly known as tooth rot, is one of the most prevalent and long- lasting dental illnesses, affecting people at all stages of their lives. There are a few different sorts of dental x-rays, each of which records a different perspective on dental living systems for caries detection and has the highest symptomatic accuracy, whereas panoramic radiography has the lowest Despite this, Bitewing has a few downsides, such as patient unease. Because of the lack of knowledge among administrators, Bitewing imaging frequently results in increased patient radiation exposure as a result of the need for image retakes. On the other hand, panoramic x-ray scans, also known as Orthopantomogram (OPG), are commonly utilized to capture the whole mouth with a small amount of radiation. OPG has a low radiation content, is simple to use, takes less time, and provides exceptional patient comfort. In this way, when compared to intraoral frameworks, pediatric, impaired, and senior people would profit greatly from panoramic imaging frameworks. This research work explores panoramic photos to detect accurate dental disease using deep learning. As a result, most patients can benefit from panoramic imaging, which covers a large portion of the maxillofacial region, including all of the teeth.

关键词： Deep learning Lacquers Visualization Laplace equations Teeth X-rays Learning (artificial intelligence)

Cybersecurity Enhancement in IoT-Enabled Public Health Information Systems Using Deep Learning Techniques

学校读者我要写书评

暂无评论

Cybersecurity Enhancement in IoT-Enabled Public Health Infor...

AI-Driven Smart Healthcare for Society 5.0

作者： Mahesh Kumar Mishra Lalit Mohan Trivedi Mansoor Farooq Divya Nimma Malik Bader Alazzam B Kiran Bala Sr SAP Consultant Delta System and Software Inc Texas USA Department of ASH Moradabad Institute of Technology Moradabad UP India Department of Cybersecurity American University of Bahrain Bahrain PhD in Computational Science University of Southern Mississippi Data Analyst in UMMC USA Faculty of Information Technology Jadara University Irbid Jordan Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331536336

ISBN: (纸本)9798331536343

The rising use of IoT devices in Public Health Information Systems (PHIS) has revolutionized the way patient surveillance and record keeping is being done in real-time, but this has exposed systems to serious cybersecurity threats. Generated by using traditional approaches, like rule-based detection and basic artificial neural network-based models, is not capable of dealing with the dynamic and diverse nature of threats in IoT networks. These approaches are often inadequate in providing a detailed analysis of the attack especially because they do not have the ability to learn from sequences of features. This work presents an improved predictive analytics model using CNN with BiLSTM to improve cybersecurity in IoT connected PHIS. The CNN component performs feature extraction on spatial elements in the data received while the BiLSTM uncovers temporal dependencies and sequence of attacks, which enhance threats identification accuracy. The process of the proposed methodology includes dataset acquisition and cleansing of IoT healthcare datasets and finally, the training and testing of the model with the help of relevant parameter such as accuracy, precision, and recall values. Qualitative comparison with the baseline models also shows that the proposed hybrid CNN-BiLSTM model performs better, and it has fewer false alarms to detect a range of cyber threats. Accordingly, the results point to a feasible solution for enhancing security and reliability of IoT-based healthcare applications to protect patients’ record from cyber threats.

关键词： Training Accuracy Surveillance Bidirectional long short term memory Threat assessment Internet of Things Computer security Public healthcare Information systems Testing

Comparative Analysis of Deep Learning Models for Multilingual Language Translation

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning Models for Multilingua...

Artificial Intelligence (SLAAI-ICAI), SLAAI International Conference on

作者： Divya Nimma V. K. Somasekhar Srinivas Santoshi Sen Gupta Hari Nair R. Latha Devi B. Kiran Bala Department Computational Science Data Analyst in UMMC University of Southern Mississippi USA Department of Mathematics Mohan Babu University Tirupati Rangampeta India School of Management Graphic Era Hill University Bhimtal Adjunct Professor Graphic Era Deemed to be University Dehradun Uttarakhand India Department of English Sagi Rama Krishnam Raju Engineering College (A) Bhimavaram A.P. India Department of English University College of Engineering (Anna University constituent College) Nagercoil India Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331509170

ISBN: (纸本)9798331509187

Multilingual language translation is a crucial undertaking in herbal language processing (NLP), facilitating pass-linguistic verbal exchange and know-how. Existing deep getting to know models, including Transformers, Multilingual BERT (mBERT), and mBART, have proven sizable advancements in translation satisfactory; however, they come with boundaries. Standard Transformers and mBERT models regularly struggle with low-resource languages and 0-shot translation situations because of their reliance on substantial parallel corpora or confined language representation. To cope with those drawbacks, a singular method is proposed that mixes the strengths of the mBART and M2M-100 architectures. This method leverages a hybrid version structure incorporating a chain-to-sequence Transformer framework more suitable with go-lingual switch mastering and information augmentation techniques. The approach allows higher performance in low-aid language settings and extra correct translations across non-English language pairs. The proposed methodology entails pre-education on a diverse set of multilingual datasets accompanied by using pleasant-tuning with augmented low-useful resource language records. Experimental consequences display that this model outperforms current fashions like mBART and M2M-100 via 12% in BLEU ratings for low-resource languages and achieves trendy performance in many-to-many translation duties. Additionally, the model well-known shows more suitable efficiency and scalability, making it suitable for real-world multilingual applications. This research contributes to the development of extra sturdy and efficient multilingual translation systems, paving the way for stepped forward movelingual verbal exchange in numerous international contexts.

关键词： Training Translation Scalability Noise reduction Computer architecture Switches Transformers Robustness Multilingual Standards

USED: Universal Speaker Extraction and Diarization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ao, Junyi Yıldırım, Mehmet Sinan Tao, Ruijie Ge, Meng Wang, Shuai Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore117549 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab Department of Computer Science and Engineering China MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker’s voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating ‘who spoke when’. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about ‘who spoke what and when’, which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Frequency domain analysis

HOW DOES THE BRAIN COMPUTE WITH PROBABILITIES?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Haefner, Ralf M. Beck, Jeff Savin, Cristina Salmasi, Mehrdad Pitkow, Xaq Department of Brain and Cognitive Sciences University of Rochester RochesterNY United States Department of Neurobiology Duke University DurhamNC United States Departments of Neural Science and Data Science New York University New YorkNY United States Gatsby Computational Neuroscience Unit Max Planck UCL Centre for Computational Psychiatry and Ageing Research University College London United Kingdom Neuroscience Institute Department of Machine Learning Carnegie Mellon University PittsburghPA United States Department of Neuroscience Center for Neuroscience and Artificial Intelligence Baylor College of Medicine HoustonTX United States Department of Electrical and Computer Engineering Department of Computer Science Rice University HoustonTX United States

This perspective piece is the result of a Generative Adversarial Collaboration (GAC) tackling the question 'How does neural activity represent probability distributions?'. We have addressed three major obstacles to progress on answering this question: first, we provide a unified language for defining competing hypotheses. Second, we explain the fundamentals of three prominent proposals for probabilistic computations - Probabilistic Population Codes (PPCs), Distributed Distributional Codes (DDCs), and Neural Sampling Codes (NSCs) - and describe similarities and differences in that common language. Third, we review key empirical data previously taken as evidence for at least one of these proposal, and describe how it may or may not be explainable by alternative proposals. Finally, we describe some key challenges in resolving the debate, and propose potential directions to address them through a combination of theory and *** Codes 92 Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks