检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language Processing 2024年 33卷 528-541页

作者： Ammar Amjad Sucharita Khuntia Hsien-Tsung Chang Li-Chia Tai Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan Bachelor Program in Artificial Intelligence Chang Gung University Taoyuan Taiwan Department of Physical Medicine and Rehabilitation Chang Gung Memorial Hospital Taoyuan Taiwan Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

As artificial intelligence advances, speech-emotion recognition (SER) has become a critical research area. Traditional SER methods typically rely on homogeneous domain data for training and testing. This practice requires adaptation when confronted with real-world data's heterogeneous linguistic, methodological, and speaker-related attributes. These variances can degrade the accuracy and generalization of SER models. To address this gap, we introduce a novel domain adaptation technique, multi domain emotion recognition enhancement (MDERE), which utilizes a non-negative matrix to reduce the inflexibility of the conventional binary label matrix for source domain data. This process yields a label matrix that better adapts to the nuances of the source labels while preserving their original structure. This framework refines SER methods by fine-tuning a transformation matrix for enhanced emotion discrimination. Elastic net regularization, which combines L1 and L2 penalties, enriches the transformation matrix, selectively emphasizing relevant features to enhance the robustness of emotion detection. The framework constructs customized similarity and dissimilarity graphs to reconcile the differences between source and target domains, enabling nuanced cross-domain data analysis. Extensive testing on multiple cross-domain SER tasks has shown that MDERE substantially improves recognition accuracy, surpassing several state-of-the-art algorithms. These results demonstrate MDERE's ability to effectively align domain variations enhances the generalizability of SER systems.

关键词： Emotion recognition Speech processing Speech recognition Training Adaptation models Testing Sparse matrices Linear regression Accuracy Vectors

来源：评论

学校读者我要写书评

暂无评论

Informative and Long-Term Response Generation using Multiple Suggestions and User Persona Retrieval in a Dialogue System

引用

APSIPA Transactions on Signal and Information Processing 2024年第2期13卷

作者： Hsu, Jia-Hao Chen, Tsai-Yi Wu, Chung-Hsien Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Artificial Intelligence National Cheng Kung University Tainan Taiwan

Enhancing user satisfaction in dialogue systems relies on their ability to understand users and generate responses that meet their expectations. This study proposes a dialogue system that incorporates the Multi-Suggestions Transformer (MST) to generate informative and long-term responses. The MST combines empathy suggestions, system persona suggestions, and knowledge suggestions to produce comprehensive and informative responses. Additionally, the system employs a persona detection model and a persona extraction model to extract the user persona from current sentences and retrieve the most suitable user persona from the dialogue history. This facilitates long-term conversations by enabling the system to remember and respond to sentences relevant to the user persona. The proposed MST-based dialogue system outperforms the baseline in terms of informativeness, as evidenced by higher scores in BLEU, BERT-score, Distinct-n, and Perplexity on the Blended Skill Talk and Multi Session Chat datasets. Furthermore, two novel evaluation metrics, PerP and PerB, introduced in this study demonstrate the system’s effective utilization of the user persona for achieving long-term dialogue. Human subjective evaluation indicates that our model consistently outperforms the baseline, achieving superior scores of 68%, 56%, 52%, and 64% in the four subjective metrics. © 2024 J.-H. Hsu, T.-Y. Chen and C.-H. Wu.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Hardware Accelerator of Morphological Image Processor

Reconfigurable Hardware Accelerator of Morphological Image P...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Ming-Yi Lin Sheng-Hsien Hsieh Ching-Han Chen Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan Bachelor's Program in Artificial Intelligence and Mechatronics National Pingtung University of Science and Technology Pingtung Taiwan Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan

Researchers emphasize the importance of hardware accelerators for mathematical morphology. If there are any issues, the hardware architecture may need to be redesigned. Thus, we propose a novel, reconfigurable hardware architecture with pipeline techniques for acceleration. With the order control register, there is no need to modify the architecture even if different results are expected. Furthermore, the hardware architecture caters to specific purposes instead of requiring a purpose-built hardware design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Multi-Task Learning Based on One Stage YOLOR Algorithm 32

Asynchronous Multi-Task Learning Based on One Stage YOLOR Al...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Liou, Cheng-Fu Lee, Tsung-Han Guo, Jiun-In National Yang Ming Chiao Tung University Graduate Degree Program of College of Electrical and Computer Engineering Hsinchu Taiwan Wistron-NCTU Embedded Artificial Intelligence Research Center National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9798350399714

The You Only Learn One Representation (YOLOR) approach is an object detector that can encode implicit knowledge and explicit knowledge of multiple tasks simultaneously. However, the requirement of jointly feeding data is not a friendly setting for an edge device due to the high computational cost. A better strategy is to learn the concept of the new task on the device individually, one by one, without access to the old data. In other words, the model has to deal with multiple tasks asynchronously. In this work, we extend the multi-purpose network YOLOR to asynchronous multi-task learning to learn domain invariant features, which focus on capturing the relatedness between the weight of the previous task and data of the subsequent task. Further, as the number of tasks gradually increases, we accumulate significant weights by introducing task-specific masks and expert modules;the former can automatically identify important filters to prevent modification caused by new tasks, and the latter address the kernel space misalignment problem to perform multi-task feature selection. We experimentally demonstrate that the proposed training strategy significantly outperforms the traditional solution in learning multiple tasks at different times on a public dataset, which supports that the proposed approach is more competitive for resource-limited edge devices. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Leveraging Advanced computer Vision for Hazardous Behavior Monitoring on Campus Safety Maintenance 4

Leveraging Advanced Computer Vision for Hazardous Behavior M...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Tsai, Shang-Te Wu, Zong-Rong Chang, Yu-Cheng Lin, Wei-Hsin Lee, Jia-Yi Chien, Wei Business School Yulin Normal University Yulin China National Yunlin University of Science and Technology Department of Technical and Vocational Program in Artificial Intelligence Yunlin Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taoyuan Taiwan National Pingtung University Department of International Business Pintung Taiwan

ISBN: (纸本)9798350360721

There was an incident on a campus involving the casualty of students. It created social unrest and heightened concerns over campus security. Consequently, it becomes important to prevent such incidents. Thus, we developed a solution for enhancing campus security and creating a safer school environment using deep learning. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Respiratory Disease Classification by CNN using MFCC 6

Respiratory Disease Classification by CNN using MFCC

引用

6th IEEE International Conference on Computing, Communication and Automation, ICCCA 2021

作者： Mridha, Krishna Sarkar, Shakil Kumar, Dinesh Computer Engineering Marwadi University Gujarat Rajkot India Bachelor of Pharmacy Marwadi University Gujarat Rajkot India Computer Engineering Artificial Intelligence Big Data Marwadi University Rajkot India

ISBN: (纸本)9781665414739

Respiratory disease is a sort of sickness that produces a high death rate in rural or urban settings. Respiratory illnesses must be detected in advance and the rapid growth of deep learning over the last several years will lead the analysis and calculation of respiratory sound by computer computing power into a new trend of disease detection. Noting recent progress in the field of image classification, in which CNN's are utilized to categories high-precision pictures. A technique of classification of breathing sonority by CNN is proposed in this work, where it is trained. To this end, each audio sample was visually represented, enabling the identification of classification resources by applying the same methodologies to categories of high-precision pictures. We employed the Mel frequency cepstral coefficients method (MFCCs). We extracted resources with MFCC for every audio file in the dataset, meaning for every audio sample that we have an image representation. In the categorization of respiratory diseases utilized in the six classes accessible in the database, the approach described in this article achieved results over 93 percent. The six classifications are COPD (Chronic Pulmonary Obstructive Disease), Healthy, URTI (Upper Respiratory Tract Infection), Bronchiectasis, Pneumonia, Bronchiolitis. © 2021 IEEE.

关键词： Pulmonary diseases

来源：评论

学校读者我要写书评

暂无评论

Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context

arXiv

引用

arXiv 2024年

作者： Yu, Sangwon Kim, Ik-Hwan Song, Jongyoon Lee, Saehyung Park, Junsung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often struggle to filter out irrelevant documents within the context, and their performance is sensitive to the position of supporting documents within that context. In this paper, we identify an additional challenge: LLMs' performance is also sensitive to the order in which the supporting documents are presented. We refer to this as the misordered context problem. To address this issue, we propose a simple yet effective method called context repetition (CoRe), which involves prompting the model by repeatedly presenting the context to ensure the supporting documents are presented in the optimal order for the model. Using CoRe, we improve the F1 score by up to 30%p on multi-hop QA tasks and increase accuracy by up to 70%p on a synthetic task. Additionally, CoRe helps mitigate the well-known "lost-in-the-middle" problem in LLMs and can be effectively combined with retrieval-based approaches utilizing Chainof- Thought (CoT) reasoning. Copyright © 2024, The Authors. All rights reserved.

关键词： Context sensitive languages

来源：评论

学校读者我要写书评

暂无评论

Fully Geometric Panoramic Localization

Fully Geometric Panoramic Localization

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Junho Kim Jiwon Jeong Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Dept. of Electrical Engineering Stanford University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines. Given a pre-captured 3D map, our approach localizes a panorama image, taking advantage of the holistic 360° view. The system mitigates potential privacy breaches or domain discrepancies by avoiding trained or hand-crafted visual descriptors. However, as lines alone can be ambiguous, we express distinctive yet compact spatial contexts from relationships between lines, namely the dominant directions of parallel lines and the intersection between non-parallel lines. The resulting representations are efficient in processing time and memory compared to conventional visual descriptor-based methods. Given the groups of dominant line directions and their intersections, we accelerate the search process to test thousands of pose candidates in less than a millisecond without sacrificing accuracy. We empirically show that the proposed 2D-3D matching can localize panoramas for challenging scenes with similar structures, dramatic domain shifts or illumination changes. Our fully geometric approach does not involve extensive parameter tuning or neural network training, making it a practical algorithm that can be readily deployed in the real world. Project page including the code is available through this link: https://***/fgpl/.

关键词： Location awareness Geometry Training Visualization Accuracy Three-dimensional displays Pipelines

来源：评论

学校读者我要写书评

暂无评论

Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach

arXiv

引用

arXiv 2024年

作者： Lee, Saehyung Yu, Sangwon Park, Junsung Yi, Jihun Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task. Our methodology, PlugIR, actively utilizes the general instruction-following capability of LLMs in two ways. First, by reformulating the dialogue-form context, we eliminate the necessity of fine-tuning a retrieval model on existing visual dialogue data, thereby enabling the use of any arbitrary black-box model. Second, we construct the LLM questioner to generate non-redundant questions about the attributes of the target image, based on the information of retrieval candidate images in the current context. This approach mitigates the issues of noisiness and redundancy in the generated questions. Beyond our methodology, we propose a novel evaluation metric, Best log Rank Integral (BRI), for a comprehensive assessment of the interactive retrieval system. PlugIR demonstrates superior performance compared to both zero-shot and fine-tuned baselines in various benchmarks. Additionally, the two methodologies comprising PlugIR can be flexibly applied together or separately in various situations. Our codes are available at https://***/Saehyung-Lee/PlugIR. © 2024, CC BY.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Gender Detection from Hand Palm Images: A PySpark-Driven Approach with VGG19 Feature Extraction and MLP Classification

Gender Detection from Hand Palm Images: A PySpark-Driven App...

引用

Computing and Informatics (ICCI), International Conference on

作者： Mayar Tarek Henedak Ganna Waleed Ezzeldin Nada Adel Mohamed Malak Essam Hamed Sarah Mahmoud ElMasarawi Shahd Mohamed Fekry Tawfik Yasser Khaled M. Fouad Mostafa Fathi Ibrahim Abdelbaky BMD Program ITCS Nile University Giza Egypt AI Program ITCS Nile University Giza Egypt Faculty of Computers and Artificial Intelligence Benha University Faculty of Computer Science and Engineering New Mansoura University Computer Science Program ITCS Nile University Giza Egypt Artificial Intelligence Department Faculty of Computers and Artificial Intelligence Benha University Banha Egypt

This paper presents a comprehensive methodology for gender detection using hand palm images, leveraging image processing techniques and PySpark for scalable and efficient processing. The approach encompasses a meticulous image preprocessing pipeline, incorporating essential stages like grayscale conversion, the application of the Difference of Gaussians (DoG) filter, and adaptive histogram equalization. This approach not only refines image features but also ensures scalability, accommodating large datasets seamlessly. After preprocessing of hand images, the VGG19 model is employed as a powerful feature extractor, utilizing its pre-trained convolutional layers to capture high-level abstract features from hand palm images. The final step was to train and fit the tabular data and extracted features on the Multilayer Perceptron (MLP) model, which is a feedforward neural network for classification tasks in PySpark. The MLP model, with its ability to learn complex patterns, proves effective in accurately predicting gender categories based on the extracted features. Finally, the model results were 94% accuracy for training and 87% testing which indicates that the model is generalizing well to unseen data. Also, another evaluation metrics were used like Precision 0.87, Recall 0.87, F1 Score 0.87 and AUC 0.92.

关键词：

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：