检索结果-内蒙古大学图书馆

QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 1-12页

作者： Guo, Haohan Xie, Fenglong Kang, Jiawen Xiao, Yujia Wu, Xixin Meng, Helen Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong SAR China Xiaohongshu Beijing China Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong SAR China Stanley Ho Big Data Decision Analytics Research Centre The Chinese University of Hong Kong Hong Kong SAR China

This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS quality with lower supervised data requirements via Vector-Quantized Self-Supervised Speech Representation Learning (VQ-S3RL) utilizing more unlabeled speech audio. This framework comprises two VQ-S3R learners: first, the principal learner aims to provide a generative Multi-Stage Multi-Codebook (MSMC) VQ-S3R via the MSMC-VQ-GAN combined with the contrastive S3RL, while decoding it back to the high-quality audio;then, the associate learner further abstracts the MSMC representation into a highly-compact VQ representation through a VQ-VAE. These two generative VQ-S3R learners provide profitable speech representations and pre-trained models for TTS, significantly improving synthesis quality with the lower requirement for supervised data. QS-TTS is evaluated comprehensively under various scenarios via subjective and objective tests in experiments. The results powerfully demonstrate the superior performance of QS-TTS, winning the highest MOS over supervised or semi-supervised baseline TTS approaches, especially in low-resource scenarios. Moreover, comparing various speech representations and transfer learning methods in TTS further validates the notable improvement of the proposed VQ-S3RL to TTS, showing the best audio quality and intelligibility metrics. The trend of slower decay in the synthesis quality of QS-TTS with decreasing supervised data further highlights its lower requirements for supervised data, indicating its great potential in low-resource scenarios. IEEE

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation Models with Attention-Based Dropout Layer

引用

Computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr Safdar Abbas Khan Muhammad Ali Tahir Muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU

来源：评论

学校读者我要写书评

暂无评论

Non-Local Technique on Deep Attentive Face Super-Resolution Network 22

Non-Local Technique on Deep Attentive Face Super-Resolution ...

引用

22nd International Symposium on Communications and Information Technologies, ISCIT 2023

作者： Hajian, Amir Aung, Hein Htet Ruangsang, Watchara Chen, Sovann Aramvith, Supavadee Chulalongkorn University Department of Electrical Engineering Bangkok Thailand Multimedia Data Analytics and Processing Research Unit Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok10330 Thailand

ISBN: (纸本)9781665457316

Recent Face Super-resolution (FSR) based on iterative collaboration between facial image recovery network and landmark estimation has succeeded in super-resolving facial images. However, the existing noise in coarse features at the low-level feature extraction leads to inaccurate facial priors such as landmarks and component maps, consequently degrading the super-resolved face image on a large scale. This paper proposes, a Non-local technique for deep attentive face super-resolution network (NLDA). A Non-local module has been designed before the residual channel attention block (RCAB) to eliminate noise degradation on coarse features effectively. The proposed model optimizes feature extraction and improves facial landmark fusion to yield higher-quality super-resolved images. This approach facilitates more accurate landmark estimation and boosts the performance of our model on a large scale and various face poses. Quantitative and qualitative experiments over CelebA and Helen face image datasets show that the proposed method outperforms other state-of-the-art FSR methods in recovering high-quality face images in various face poses and at a large scale. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Cybersecurity Provision for Scalable Heterogeneous Network:A Comprehensive Survey

引用

Computer Modeling in engineering & Sciences 2024年第1期138卷 43-123页

作者： Md.Shohidul Islam Md.Arafatur Rahman Mohamed Ariff Bin Ameedeen Husnul Ajra Zahian Binti Ismail Jasni Mohamad Zain Faculty of Computing Universiti Malaysia PahangKuantan26600Malaysia School of Engineering Computing&Mathematical SciencesUniversity ofWolverhamptonWolverhamptonUK Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Komplek Al-KhawarizmiUniversiti Teknologi MARAShah AlamSelangor40450Malaysia

Blockchain-enabled cybersecurity system to ensure and strengthen decentralized digital transaction is gradually gaining popularity in the digital era for various areas like finance,transportation,healthcare,education,and supply chain *** interactions in the heterogeneous network have fascinated more attention due to the authentication of their digital application ***,the exponential development of storage space capabilities across the blockchain-based heterogeneous network has become an important issue in preventing blockchain distribution and the extension of blockchain *** is the biggest challenge of data integrity and scalability,including significant computing complexity and inapplicable latency on regional network diversity,operating system diversity,bandwidth diversity,node diversity,etc.,for decision-making of data transactions across blockchain-based heterogeneous *** security and privacy have also become the main concerns across the heterogeneous network to build smart IoT *** address these issues,today’s researchers have explored the potential solutions of the capability of heterogeneous network devices to perform data transactions where the system stimulates their integration reliably and securely with *** key goal of this paper is to conduct a state-of-the-art and comprehensive survey on cybersecurity enhancement using blockchain in the heterogeneous *** paper proposes a full-fledged taxonomy to identify the main obstacles,research gaps,future research directions,effective solutions,andmost relevant blockchain-enabled cybersecurity *** addition,Blockchain based heterogeneous network framework with cybersecurity is proposed in this paper tomeet the goal of maintaining optimal performance data transactions among ***,this paper provides an in-depth description based on the critical analysis to overcome the existing work gaps for future research where it

关键词： Blockchain cybersecurity data transaction diversity heterogeneous

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Prediction of DoD Personal Property Shipment Costs

Machine Learning Prediction of DoD Personal Property Shipmen...

引用

2023 Congress in Computer Science, Computer engineering, and Applied Computing, CSCE 2023

作者： Tucker, Tiffany Wagner, Torrey Auclair, Paul Langhals, Brent Graduate School of Engineering and Management Air Force Institute of Technology Data Analytics Certificate Program Wright-Patterson AFBOH United States LinQuest Corporation Integrated Analytics & Support BeavercreekOH United States

ISBN: (纸本)9798350327595

U.S. Department of Defense (DoD) personal property moves account for 15% of all domestic and international moves - accurate prediction of their cost could draw attention to outlier shipments and improve budget planning. In this work 136,140 shipments between 13 personal property shipment hubs from April 2022 through March 2023 with a total cost of $1.6B were analyzed. Shipment cost was predicted using recursive feature elimination on linear regression and XGBoost algorithms, as well as through neural network hyperparameter sweeps. Modeling was repeated after removing 28 features related to shipment hub location and branch of service to examine their influence on algorithm performance. The best model resulted from a neural network hyperparameter sweep on the simple 4-feature dataset. That model contained 2 hidden layers of 250 neurons, possessed a mean absolute error (MAE) of $2162 on the holdout dataset, and had an overfitting measure of 0.2%. This model's performance is a substantial improvement over a trivial mean-prediction model that possessed a MAE of $6856. Additionally, the model R2 = 0.87 compared favorably to existing work that achieved R2 = 0.73. Models that included 28 features related to shipment hub location and branch of service did not improve performance, showing that those features are insignificant in predicting shipment cost. All OLS regression and XGBoost models showed that the most influential features (in order) were weight, month of shipment, distance shipped, and days in transit. © 2023 IEEE.

关键词： ensemble methods logistics machine learning neural networks random forest regression

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Sentimental Analysis of Amazon Reviews

Machine Learning Model for Sentimental Analysis of Amazon Re...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Umamageswari, A. Pratishwaran, R.J. Poojitha Reddy, M. Yuvan Sankar Raj, R. SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering With Specialization in Big Data Analytics Ramapuram Chennai India

ISBN: (纸本)9798331522988

The goal of this project is to draw a deeper understanding of the subjective nature behind online product reviews, largely by examining a large dataset received from Amazon that contains numerous star ratings and comments. Since there is such a massive amount of data on the Amazon platform, it was perfect for the analysis. Our methodology is platform-agnostic and can be easily extended to other comparable datasets from other web platforms with comparable guarantees in achieving wide applicability. Our primary motivation is improving the dependability of online shopping. Since product reviews are currently widely used by many consumers as guides in making decisions to buy products, such reviews ought to be fair representations of the actual dependability and quality of the products. The goal of our effort is to identify patterns in the language and ratings of such reviews that would directly reflect the real customer sentiment and also the reliability of the product. Our approach has yielded already a rate of about 92%, which shows it has the potential greatly to raise the legitimacy of online reviews. We'd like to make our customers feel more confident and better equipped with information to make better and safer purchases on a website like Amazon and others. In the final analysis, we strive to make online shopping for our customers worldwide safer and more trustworthy. © 2024 IEEE.

关键词： data reliability

来源：评论

学校读者我要写书评

暂无评论

Intelligent E-Commerce Chatbot for Personalized Product Recommendations Using Text Mining and Machine Learning 2

Intelligent E-Commerce Chatbot for Personalized Product Reco...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Minu, M.S. Adithya Kavya SreeRanjini Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering with Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9798331541217

Innovative technology solutions have been developed in response to the growing need for effective and customized client contact on e-commerce platforms. This work introduces an intelligent chatbot system that uses machine learning and text mining techniques to improve user satisfaction and answer customer concerns. Advanced Natural Language Processing (NLP) models have been trained on large datasets, allowing for precise user intent interpretation and pertinent product recommendations. A strong recommendation engine is included into the system architecture to aid in decision-making, ultimately enhancing the customer experience by providing individualized, real-time help. The study also highlights the significance of data privacy by using privacy-preserving techniques to safeguard user data. The system's scalability and performance benefits are highlighted through thorough comparisons with current models. By showcasing the useful uses of machine learning and text mining in enhancing customer contact and service delivery, this study makes a substantial contribution to the development of AI-driven solutions in e-commerce. © 2024 IEEE.

关键词： Big data Chatbot Cost data Mining e-Commerce Hadoop Machine Learning Product Purchasing Recommendation

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Meteorological Effects on Forecasting Daily Lightning Occurrence at Cape Canaveral Space Force Station

Atmospheric Meteorological Effects on Forecasting Daily Ligh...

引用

2023 Congress in Computer Science, Computer engineering, and Applied Computing, CSCE 2023

作者： Saul, Jon Wagner, Torrey Mbonimpa, Eric Langhals, Brent Graduate School of Engineering and Management Air Force Institute of Technology Data Analytics Certificate Program Wright-Patterson AFBOH United States

ISBN: (纸本)9798350327595

As the Cape Canaveral Space Force Station and Kennedy Space Center increase their launch rate, any process that could assist in the automation of the currently-manual lightning forecast would be valuable. This work examines the possibility of machine-learning assistance with the daily lighting forecast which is produced by the 45th Weather Squadron. A dataset consisting of 34 lightning, pressure, temperature and windspeed measurements taken from 334 daily weather balloon (rawinsonde) launches in the timeframe 2012-2021 was examined. Models were created using recursive feature elimination on logistic regression and XGClassifier algorithms, as well as Bayesian and bandit optimization of neural network (NN) hyperparameters. The modeling process was repeated after eliminating 13 features related to windspeed. The best performing models on both datasets were the optimized NN models, with an F1 metric of 0.79 on the full dataset and 0.66 on the reduced dataset. For comparison, a model that predicted randomly achieved F1 = 0.47 on this dataset. The addition of 13 windspeed-related features more than doubled the complexity of the 21-feature no-wind model while increasing model performance by 13 percentage points. A notable inference from the statistical modeling is that the most important feature from both datasets was the Thompson convective index, which is related to temperature, dewpoint, relative humidity and lapse rate. © 2023 IEEE.

关键词： launch operations lightning forecast lightning indices neural network

来源：评论

学校读者我要写书评

暂无评论

Fast Moving Consumer Goods Object Detection Using YOLOV8

Fast Moving Consumer Goods Object Detection Using YOLOV8

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Umamageswari, A. Mukund, P.U. Abhishek, V.B. Devi Vaishnavi, Y. SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering With Specialization in Big Data Analytics Ramapuram Chennai India

ISBN: (纸本)9798331522988

The basis of this project is to investigate whether the YOLO, an object detection algorithm where 'You Only Look Once' constitutes the name, could be applied to develop FMCG management;together with the management of FMCG, it becomes the gateway to increasing retail precision, efficiency, and agility. Under real-time processing, the system detects and counts FMCG products on retail shelves with an accuracy rate of 92.5%. This accuracy ensures that the optimum stock levels are maintained and there will be no discrepancies. The system processes video feeds at 0.08 seconds per frame, thus allowing inventory data to be updated in real-time to enable quick, data-driven decisions. YOLO's flexibility ensures consistent performance across different store layouts and product types. This system integrates with other retail management tools and allows integrating inventory data in the real time. This means that it would be made available with invaluable insights which would prevent stock depletion while helping to curtail costs. This project takes YOLO ahead of just being a game changer in the FMCG inventory management while operating to reduce expenses and customer satisfaction due to product availability. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Knowledge Leaks in data-Driven Business Models? Exploring Different Types of Knowledge Risks and Protection Measures

引用

Schmalenbach Journal of Business Research 2024年第3期76卷 357-396页

作者： Fruhwirth, Michael Pammer-Schindler, Viktoria Thalmann, Stefan Know-Center GmbH Institute for Interactive Systems and Data Science Faculty of Computer Science and Biomedical Engineering Graz University of Technology Silicon Austria Labs GmbH Business Analytics and Data Science-Center (BANDAS-Center) School of Business Economics and Social Sciences University of Graz

data-driven business models imply the inter-organisational exchange of data or similar value objects. data science methods enable organisations to discover patterns and eventually knowledge from data. Further, by training machine learning models, knowledge is materialised in those models. Thus, organisations might risk the exposure of competitive knowledge by sharing data-related value objects, such as data, models or predictions. Although knowledge risks have been studied in traditional business models, little research has been conducted in the direction of data-driven business models. In this explorative qualitative study, we conducted 28 expert interviews in three rounds (two exploratory and one evaluatory) and identified five types of risks along the three basic types of value objects: data, models and predictions. These risks depend on the context, i.e., when competitive knowledge could be discovered from shared value objects. We found that those risks can be mitigated by technology, contractual regulations, trusted relationships, and adjusting the business model design. In this study, we show that the risk of knowledge leakage is a relevant risk factor in data-driven business models. Overall, knowledge risks should be considered already during business model design, and their management requires an interdisciplinary approach via a balanced assessment. The level of knowledge protection from a technology perspective highly depends on computer science innovations and thus is a moving target. As an outlook, we suggest that knowledge risk will become even more relevant with the extensive usage of machine learning and artificial intelligence in data-driven business models. © The Author(s) 2024.

关键词： Business model innovation data analytics data-driven business models Knowledge risks Risk management Value objects

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：