检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Sungwon Kim Kevin J Shih Rohan Badlani João Felipe Santos Evelina Bhakturina Mikyas Desta Rafael Valle Sungroh Yoon Bryan Catanzaro NVIDIA and Department of Electrical and Computer Engineering Seoul National University NVIDIA Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

While recent large-scale neural codec language models have shown significant improvement in zero-shot TTS by training on thousands of hours of data, they suffer from drawbacks such as a lack of robustness, slow sampling speed similar to previous autoregressive TTS methods, and reliance on pre-trained neural codec representations. Our work proposes P-Flow, a fast and data-efficient zero-shot TTS model that uses speech prompts for speaker adaptation. P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis. Our speech-prompted text encoder uses speech prompts and text input to generate speaker-conditional text representation. The flow matching generative decoder uses the speaker-conditional output to synthesize high-quality personalized speech significantly faster than in real-time. Unlike the neural codec language models, we specifically train P-Flow on LibriTTS dataset using a continuous mel-representation. Through our training method using continuous speech prompts, P-Flow matches the speaker similarity performance of the large-scale zero-shot TTS models with two orders of magnitude less training data and has more than 20× faster sampling speed. Our results show that P-Flow has better pronunciation and is preferred in human likeness and speaker similarity to its recent state-of-the-art counterparts, thus defining P-Flow as an attractive and desirable alternative. We provide audio samples on our demo page https://***/labs/adlr/projects/pflow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

引用

computers, Materials & Continua 2024年第1期78卷 1363-1379页

作者： Kwok Tai Chui Brij B.Gupta Varsha Arya Miguel Torres-Ruiz School of Science and Technology Hong Kong Metropolitan UniversityHong Kong999077China Department of Computer Science and Information Engineering Asia UniversityTaichung41354Taiwan Center for Advanced Information Technology Kyung Hee UniversitySeoul02447Korea Symbiosis Centre for Information Technology Symbiosis International UniversityPuneMaharashtra411042India Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon School of Computing Skyline University CollegeSharjah1797United Arab Emirates Department of Business Administration Asia UniversityTaichung41354Taiwan Center for Interdisciplinary Research University of Petroleum and Energy StudiesDehradun248007India Department of Computer Science&Engineering Chandigarh UniversityChandigarh160036India Centro de Investigación en Computación Instituto Politécnico NacionalUPALM-ZacatencoMexico City07320Mexico

The visions of Industry 4.0 and 5.0 have reinforced the industrial *** have also made artificial intelligence incorporated as a major *** machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe *** learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two *** response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning *** is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative *** algorithm also adaptively adjusts the portion of training data to balance the learning rate and training *** proposed algorithm is evaluated and analyzed using ten benchmark *** with other algorithms from existing works,SA-ITL improves the accuracy of all *** studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

关键词： Deep learning incremental learning machine fault diagnosis negative transfer transfer learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of User Review on Indonesian Food and Beverage Group using Machine Learning Techniques

Sentiment Analysis of User Review on Indonesian Food and Bev...

引用

2022 IEEE Creative Communication and Innovative Technology, ICCIT 2022

作者： Yanfi, Yanfi Heryadi, Yaya Lukas, Lukas Suparta, Wayan Arifin, Yulyani Bina Nusantara University Binus Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9781665468763

A vast number of technologies based on Artificial Intelligence (AI) have proliferated into various application domains. As part of its objectives to develop agents which can behave and think like humans, some branches of AI have focused on developing various algorithms that can learn from input data without explicitly being programmed. In the food industry, notably in restaurants, smartphone technology is typically used to collect data from customers efficiently such as orders or feedback toward the services provided. The use of smartphones by some restaurants is motivated by their convenience and efficiency. Furthermore, various promotions, discounts, and membership benefits offered by cellular service providers have attracted the use of smartphones as devices for improving restaurant services to their customers. This study aimed to conduct a sentiment analysis related to multi-brand restaurants in Indonesia based on customer feedback. The data retrieved from the Google Play Store consists of 756 reviews from Boga, Champs, Hangry, Ismaya, Kulo, and Union groups. In this study, TF-IDF was used as a vectorizer to represent customer feedback as numeric vectors. The polarity sentiment of customer feedback was recognized using classifier models based on machine learning such as Logistic Regression, Naive Bayes (NB), Random Forest, and Support Vector Machine (SVM) as the classifier. The empirical results showed that SVM has the best accuracy of 93.10 % average accuracy followed by Logistic Regression with 92.41 %, Random Forest with 84.14 % average accuracy, and Naive Bayes with 76.55 % average accuracy. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Advanced BERT and CNN-Based Computational Model for Phishing Detection in Enterprise Systems

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2165-2183页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon College of Business Administration Management DepartmentPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks present a serious threat to enterprise systems,requiring advanced detection techniques to protect sensitive *** study introduces a phishing email detection framework that combines Bidirectional Encoder Representations from Transformers(BERT)for feature extraction and CNN for classification,specifically designed for enterprise information ***’s linguistic capabilities are used to extract key features from email content,which are then processed by a convolutional neural network(CNN)model optimized for phishing *** an accuracy of 97.5%,our proposed model demonstrates strong proficiency in identifying phishing *** approach represents a significant advancement in applying deep learning to cybersecurity,setting a new benchmark for email security by effectively addressing the increasing complexity of phishing attacks.

关键词： Phishing BERT convolutional neural networks email security deep learning

来源：评论

学校读者我要写书评

暂无评论

MathReader : Text-to-Speech for Mathematical Documents

MathReader : Text-to-Speech for Mathematical Documents

引用

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

作者： Sieun Hyeon Kyudan Jung Nam-Joon Kim Hyun Gon Ryu Jaeyoung Do Department of Electrical and Computer Engineering Seoul National University Department of Mathematics Chung-Ang University NVIDIA Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions. This is because most modern academic papers are written in LaTeX, and when LaTeX formulas are compiled, they are rendered as distinctive text forms within the document. However, traditional TTS document readers output only the text as it is recognized, without considering the mathematical meaning of the formulas. To address this issue, we propose MathReader, which effectively integrates OCR, a fine-tuned T5 model, and TTS. MathReader demonstrated a lower Word Error Rate (WER) than existing TTS document readers, such as Microsoft Edge and Adobe Acrobat, when processing documents containing mathematical formulas. MathReader reduced the WER from 0.510 to 0.281 compared to Microsoft Edge, and from 0.617 to 0.281 compared to Adobe Acrobat. This will significantly contribute to alleviating the inconvenience faced by users who want to listen to documents, especially those who are visually impaired. The code is available at https://***/hyeonsieun/MathReader.

关键词： Text recognition Error analysis Pipelines Optical character recognition Graphics processing units Signal processing Real-time systems Mathematical models Text to speech Speech processing

来源：评论

学校读者我要写书评

暂无评论

Learning 3D Scene Analogies with Neural Contextual Scene Maps

arXiv

引用

arXiv 2025年

作者： Kim, Junho Bae, Gwangtak Lee, Eun Sun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open spaces, we propose teaching machines to identify relational commonalities in 3D spaces. Instead of focusing on point-wise or object-wise representations, we introduce 3D scene analogies, which are smooth maps between 3D scene regions that align spatial relationships. Unlike well-studied single instance-level maps, these scene-level maps smoothly link large scene regions, potentially enabling unique applications in trajectory transfer in AR/VR, long demonstration transfer for imitation learning, and context-aware object rearrangement. To find 3D scene analogies, we propose neural contextual scene maps, which extract descriptor fields summarizing semantic and geometric contexts, and holistically align them in a coarse-to-fine manner for map estimation. This approach reduces reliance on individual feature points, making it robust to input noise or shape variations. Experiments demonstrate the effectiveness of our approach in identifying scene analogies and transferring trajectories or object placements in diverse indoor scenes, indicating its potential for robotics and AR/VR applications. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Audio-aided Character Control for Inertial Measurement Tracking

Audio-aided Character Control for Inertial Measurement Track...

引用

46th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2025

作者： Jang, Hojun Bae, Jinseok Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

ISBN: (纸本)9783038682684

Physics-based character control generates realistic motion dynamics by leveraging kinematic priors from large-scale data within a simulation engine. The simulated motion respects physical plausibility, while dynamic cues like contacts and forces guide compelling human-scene interaction. However, leveraging audio cues, which can capture physical contacts in a costeffective way, has been less explored in animating human motions. In this work, we demonstrate that audio inputs can enhance accuracy in predicting footsteps and capturing human locomotion dynamics. Experiments validate that audio-aided control from sparse observations (e.g., an IMU sensor on a VR headset) enhances the prediction accuracy of contact dynamics and motion tracking, offering a practical auxiliary signal for robotics, gaming, and virtual environments. © 2025 The Authors.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Disentangled Motion Modeling for Video Frame Interpolation 39

Disentangled Motion Modeling for Video Frame Interpolation

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lew, Jaihyun Choi, Jooyoung Shin, Chaehun Jung, Dahuin Yoon, Sungroh Interdisciplinary Program in AI Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of AIIS ASRI and INMC Seoul National University Korea Republic of

ISBN: (纸本)157735897X

Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative models for improved perceptual quality. However, they require complex training and large computational costs for pixel space modeling. In this paper, we introduce disentangled Motion Modeling (MoMo), a diffusion-based approach for VFI that enhances visual quality by focusing on intermediate motion modeling. We propose a disentangled two-stage training process. In the initial stage, frame synthesis and flow models are trained to generate accurate frames and flows optimal for synthesis. In the subsequent stage, we introduce a motion diffusion model, which incorporates our novel U-Net architecture specifically designed for optical flow, to generate bi-directional flows between frames. By learning the simpler low-frequency representation of motions, MoMo achieves superior perceptual quality with reduced computational demands compared to the generative modeling methods on the pixel space. MoMo surpasses state-of-the-art methods in perceptual metrics across various benchmarks, demonstrating its efficacy and efficiency in VFI. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

DanceOnStage: positioning training of dancing stage performance in virtual reality

DanceOnStage: positioning training of dancing stage performa...

引用

IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)

作者： Ssu-Hsuan Wu Kai-Ting Wang Chia-Chen Chiang Hsin-Yu Chang Cheng-Yun Yeh Min-Chun Hu International Intercollegiate Ph.D.Program National Tsing Hua University Hsinchu Taiwan Master of Computer Science Program National Tsing Hua University Hsinchu Taiwan Interdisciplinary Program of Electrical Engineering and Computer Science National Tsing Hua University Hsinchu Taiwan Interdisciplinary Program of Technology and Art National Tsing Hua University Hsinchu Taiwan National Tsing Hua University Hsinchu Taiwan

This research aims to create a virtual reality-based practice system that simulates real-stage performance environments, assisting amateur dancers in overcoming stage fright and practicing group choreography that is difficult to achieve during individual practice. In this study, users can engage in performance simulations within the created system using the HTC VIVE virtual reality device. Within the system, we have developed a virtual stage space system that only requires a 2m x 3.5m physical area to simulate a large virtual stage experience. Users can also simulate choreographic positioning with virtual dance partners within this system, providing amateur dancers with group dance rehearsal practice opportunities that are not feasible during solo practice. Additionally, by creating three different audience modes, we aim to help users simulate various audience scenarios they may encounter during a performance. The system includes a recording feature that captures users' simulated performances, allowing them to review their actions and receive feedback after practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text Mining for Intelligent Information Processing and Analysis 3

Text Mining for Intelligent Information Processing and Analy...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Srivastav, Adarsh Indira, G. Tiwaskar, Shweta A. Garg, Avni Singh, Shweta Das, Sunanda Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350319125

textual content Mining is the process of extracting meaningful information from large volumes of unstructured text. it's far a form of synthetic intelligence used to investigate and interpret files along with consumer feedback, emails, transcripts, net logs, surveys, and on line documents. Its intention is to discover hidden shape, patterns, institutions, and correlations in textual facts in order to draw inferences and broaden new insights. textual content Mining allows a deeper level of intelligence and selection-making by means of uncovering which means from unstructured textual facts. by means of utilising present day statistical strategies and herbal Language Processing (NLP), text Mining can produce automatic fashions that interpret and translate textual content into intelligent information which can be used to make correct predictions and provide actionable insights. textual content Mining is also being used to find out new trends, categorize client sentiment, locate correlations in purchaser comments, and section document collections. eventually, text Mining is being used to assist automate selection-making by automating workflows, processing massive volumes of text in a fragment of time, and providing deep insights into patron conversations. © 2023 IEEE.

关键词： Automating Categorize Collections Conversations Insights

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：