检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,585 篇 会议
28 册 图书
24 篇 期刊文献

馆藏范围

1,637 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,111 篇 工学
- 1,019 篇 计算机科学与技术...
- 749 篇 软件工程
- 245 篇 信息与通信工程
- 90 篇 电气工程
- 69 篇 控制科学与工程
- 67 篇 生物工程
- 42 篇 化学工程与技术
- 24 篇 仪器科学与技术
- 24 篇 安全科学与工程
- 23 篇 生物医学工程（可授...
- 21 篇 交通运输工程
- 19 篇 机械工程
- 17 篇 网络空间安全
- 16 篇 电子科学与技术（可...
- 15 篇 建筑学
361 篇 管理学
- 288 篇 图书情报与档案管...
- 108 篇 管理科学与工程(可...
- 49 篇 工商管理
343 篇 理学
- 131 篇 数学
- 124 篇 物理学
- 75 篇 生物学
- 55 篇 统计学（可授理学、...
- 48 篇 系统科学
- 41 篇 化学
41 篇 教育学
- 41 篇 教育学
38 篇 法学
- 32 篇 社会学
37 篇 文学
- 31 篇 外国语言文学
30 篇 医学
- 27 篇 临床医学
- 22 篇 基础医学(可授医学...
19 篇 农学
- 17 篇 作物学
14 篇 经济学
4 篇 军事学

主题

184 篇 natural language...
64 篇 natural language...
55 篇 semantics
50 篇 web services
46 篇 sentiment analys...
42 篇 computational mo...
42 篇 accuracy
41 篇 deep learning
40 篇 information retr...
37 篇 data mining
36 篇 machine learning
36 篇 classification (...
35 篇 artificial intel...
33 篇 ontology
31 篇 speech recogniti...
31 篇 training
29 篇 data models
28 篇 semantic web
26 篇 search engines
26 篇 feature extracti...

机构

7 篇 spoken language ...
7 篇 sri lanka instit...
7 篇 faculty of compu...
6 篇 faculty of infor...
4 篇 key laboratory o...
4 篇 fujian yirong in...
4 篇 korea univ nat l...
4 篇 school of inform...
4 篇 international in...
4 篇 information engi...
3 篇 big data and art...
3 篇 graduate school ...
3 篇 national univers...
3 篇 institute of art...
3 篇 carnegie mellon ...
3 篇 school of inform...
3 篇 chitkara univers...
3 篇 beijing univ pos...
3 篇 ipswich
3 篇 department of in...

作者

7 篇 nakagawa seiichi
5 篇 ren fuji
5 篇 zhao tiejun
5 篇 rim hae-chang
4 篇 heyan huang
4 篇 shikano kiyohiro
4 篇 fuji ren
4 篇 liu ting
3 篇 li li
3 篇 rykowski jarogni...
3 篇 nakamura satoshi
3 篇 zheng dequan
3 篇 ngoc thanh nguye...
3 篇 medhat walaa
3 篇 kinshuk
3 篇 bogdan trawiński
3 篇 sun xu
3 篇 mizera-pietraszk...
3 篇 bollegala danush...
3 篇 kitsuregawa masa...

语言

1,597 篇 英文
37 篇 其他
10 篇 中文

检索条件"任意字段=6th International Conference on Advanced Language Processing and Web Information Technology"

共 1637 条记录，以下是371-380 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Single-Channel Speech Enhancement with Conformer

Single-Channel Speech Enhancement with Conformer

引用

IEEE international conference on Electronic information and Communication technology (ICEICT)

作者： Haining Wang Ying Gao Qing Zhao Shifeng Ou School of Physics and Electronic Information Yantai University Yantai Shandong Province China

the transformer model is renowned for performing well in the field of natural language processing, thanks to its capability of extracting global features. Initially, conformer model was proposed for separating continuous speech. Inheriting the transformer model's ability to extract global features, the conformer model is equipped with a convolutional layer structure that can extract local features with more efficacy. this study aims to introduce a waveform-level end-to-end single-channel speech enhancement approach based on conformer. the proposed approach is made up of three distinct components: the downsampling layer, the conformer layer, and the upsampling layer. the conformer layer is composed of multiple conformer blocks that leverage residual connections in both parallel and series. the ablation experiments demonstrate that the conformer layer with series-parallel connections significantly improves speech enhancement performance. the experimental results, employing the VoiceBank-DEMAND corpus dataset, indicate that the proposed approach outperforms other competing techniques in terms of speech enhancement performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recuperative Reference Search Aided Approach Towards Voice Cloning

Recuperative Reference Search Aided Approach Towards Voice C...

引用

international conference on Computational Intelligence and Networks (CINE)

作者： Premanand Ghadekar Ojas Joshi Jignesh Barhate Basun Kundu Arman Nandeshwar Manthan Gujar Department of Information Technology Vishwakarma Institute of Technology Pune

ISBN: (数字)9798331516796

ISBN: (纸本)9798331516802

this proposed system presents a novel approach to enhancing synthesized speech by infusing emotional nuances. By fine-tuning existing models, emotional inflections and intonations are introduced, improving perceptual evaluation of speech quality (MFCC) and mean opinion scores (MOS). the paper presents the solution of cloning life-like voice of any individual to an astounding similarity to that of original which is achieved in vocal data as small as 10 minutes in duration. the paper sees the contributions made such as use of deep invariant optimal quantization to effectively condense neural network models without compromising their performance, surpassing results in the field of RPA, RCA and OA by factors of $\mathbf{6. 2 1 \%}$, 6.9% and 2.12% respectfully with the added. the collaborative effort across machine learning, natural language processing (NLP), and audio engineering promises high-quality audio indistinguishable from human speech, with applications spanning assistive technologies to customer service solutions. this research contributes to advancing voice cloning technology, ensuring synthesized speech integrates emotional depth and authenticity effectively.

关键词： Quantization (signal) Customer services Neural networks Cloning Collaboration Machine learning Speech enhancement Natural language processing Mel frequency cepstral coefficient Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

MedNLI Is Not Immune: Natural language Inference Artifacts in the Clinical Domain 59

MedNLI Is Not Immune: Natural Language Inference Artifacts i...

引用

Joint conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th international Joint conference on Natural language processing (IJCNLP) / 6th Workshop on Representation Learning for NLP (RepL4NLP)

作者： Herlihy, Christine Rudinger, Rachel Univ Maryland Dept Comp Sci College Pk MD 20742 USA

ISBN: (纸本)9781954085534

Crowdworker-constructed natural language inference (NLI) datasets have been found to contain statistical artifacts associated with the annotation process that allow hypothesis-only classifiers to achieve better-than-random performance (Poliak et al., 2018;Gururangan et al., 2018;Tsuchiya, 2018). We investigate whether MedNLI, a physician-annotated dataset with premises extracted from clinical notes, contains such artifacts (Romanov and Shivade, 2018). We find that entailed hypotheses contain generic versions of specific concepts in the premise, as well as modifiers related to responsiveness, duration, and probability. Neutral hypotheses feature conditions and behaviors that co-occur with, or cause, the condition(s) in the premise. Contradiction hypotheses feature explicit negation of the premise and implicit negation via assertion of good health. Adversarial filtering demonstrates that performance degrades when evaluated on the difficult subset. We provide partition information and recommendations for alternative dataset construction strategies for knowledge-intensive domains.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Towards Developing an Automatic Punctuation Prediction Model for Bangla language: A Pre-trained Mono-lingual Transformer-based Approach

Towards Developing an Automatic Punctuation Prediction Model...

引用

international conference on Electrical Engineering and information & Communication technology (ICEEICT)

作者： Ayman Iktidar Hasan Murad Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chattogram Bangladesh

ISBN: (数字)9798350385779

ISBN: (纸本)9798350385786

Punctuation prediction is an essential task in natural language processing that involves determining the appropriate position of punctuation marks in a given text. Accurate punctuation contributes to better readability and understanding in the written form of a language. A significant amount of previous research work on punctuation prediction has been found in resource-enriched languages like English. For automatic punctuation prediction in Bangla, multilingual pre-trained transformer models have been used. However, the Bangla language has unique grammatical features that make automatic punctuation prediction challenging using multi-lingual pre-trained transformer models. In this research work, we have proposed an automatic punctuation prediction approach for the Bangla language using a mono-lingual pre-trained transformer model specifically designed for Bangla. By modifying an existing dataset with four punctuation classes, a new Bangla dataset has been developed with five punctuation classes: Comma, Period, Question, Exclamation, and Others. Using the new dataset, we have trained and evaluated different versions of mono-lingual transformer-based models for automatic punctuation prediction in Bangla. We have found the state-of-the-art result for Bangla using BanglaBert-large with an F1 score of 0.89 for the existing dataset. Our model has attained an F1 score of 0.74 across the five punctuation classes providing state-of-the-art results.

关键词： Predictive models Transformers Natural language processing Communications technology Task analysis

来源：评论

学校读者我要写书评

暂无评论

Speaker Adaption with Intuitive Prosodic Features for Statistical Parametric Speech Synthesis 22

Speaker Adaption with Intuitive Prosodic Features for Statis...

引用

6th international conference on Digital Signal processing, ICDSP 2022

作者： Cheng, Pengyu Ling, Zhenhua National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China China

ISBN: (纸本)9781450395809

In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. the intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy considering that they are directly related with the overall prosodic characteristics of different speakers. the intuitive prosodic features are extracted at utterance-level or speaker-level, and are further integrated into the existing speaker-encoding-based and speaker-embedding-based adaptation frameworks respectively. the acoustic models are sequence-to-sequence ones based on Tacotron2. Intuitive prosodic features are concatenated with text encoder outputs and speaker vectors for decoding acoustic features. Experimental results have demonstrated that our proposed methods can achieve better objective and subjective performance than the baseline methods without intuitive prosodic features. Besides, the proposed speaker adaption method with utterance-level prosodic features has achieved the best similarity of synthetic speech among all compared methods. © 2022 ACM.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

StutterAI: Virtual Assistant for Stutter Detection and Analysis through Machine Learning and Natural language processing Approaches

StutterAI: Virtual Assistant for Stutter Detection and Analy...

引用

Advancements in Computing (ICAC), international conference on

作者： B.A.T.P. Benthota Arachchi J.M.I.P. Sanjeewa H.M.A.H. Wijesooriya M.C. Chandrasena Jenny Kishara thamali Kelegama V.M. Rajapakse Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Audiologist and Speech Language Pathologist Medcon (pvt) ltd Nugegoda Sri Lanka

Stutter AI is an innovative research project that focuses on the development of a web application designed to detect and provide personalized treatments for individuals with varying degrees of stuttering severity. Stuttering, characterized by disruptions in speech flow, can significantly impact communication and confidence. the Stutter AI web app utilizes advanced voice analysis techniques, natural language processing, and machine learning algorithms to analyze speech patterns, identify stuttering types, and assess severity at the phrase and syllable levels of patients aged between eighteen to forty-five. Based on this analysis, the app generates tailored treatment suggestions, incorporating evidence-based techniques to support individuals in managing and improving their fluency. through its user-friendly interface and comprehensive approach, Stutter AI aims to empower individuals who stutter, while also providing valuable insights to speech-language therapists and researchers in the field of stuttering therapy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Edge Collaborative Chinese Black Industry Jargon processing Method Based on Lightweight Transfer Learning

Cloud-Edge Collaborative Chinese Black Industry Jargon Proce...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE international conference on

作者： Wenlin Xu Jianbin Zhang Shanshan Wang Xinrong Cha University of Jinan Jinan China Yunnan Normal University Kunming China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

In order to solve the problem that pre-trained language models (PLMs) cannot be run and trained on edge devices due to the large number of parameters, lightweighting is introduced and the migration module and the large pre-trained language model are deployed separately to achieve an efficient cloud-edge collaborative transfer learning framework. Make use of the box mentioned It is possible to migrate the representation of large pre-trained language models to downstream tasks with only a few parameters fine-tuned, and can also perform cross-domain cloud edges. Collaborative reasoning. Downstream tasks in multiple domains can share the same pre-trained language model collaboratively, which can effectively save computing overhead. Tasks can be divided efficiently. Separate deployment on different devices to achieve separate deployment of multiple tasks and sharing of pre-trained models. Experiments were made on 4 datasets of public natural language tasks. the results show that the performance of the framework can reach more than 95% of that of the fully fine-tuned BERT method.

关键词： Performance evaluation Industries Computational modeling Transfer learning Collaboration Optimization methods Multitasking Natural language processing Delays Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Multilingual Cyberbullying Classification for Social Platforms

Multilingual Cyberbullying Classification for Social Platfor...

引用

international conference on Electrical Engineering and information & Communication technology (ICEEICT)

作者： Amiruzzaman Arafat Rahman Afia Farjana Hafizur Rahman Chowdhury

ISBN: (数字)9798350385779

ISBN: (纸本)9798350385786

the prevalence of cyberbullying is increasing on social media platforms, impacting individuals from many cultural backgrounds and linguistic communities. this surge is particularly evident in Asian nations. this paper explores the development of a sophisticated multilingual cyberbullying categorization system specifically designed for various social networks. the research uses modern natural language processing methods to address the worldwide issue of online harassment. It carefully examines linguistic trends in different languages. the novelty of this paper lies in its analysis of multiple languages which enables the method to be more accurate, versatile and culturally aware of different cyberbullying instances. Also, the utilization of diverse models enhances its efficacy. Specifically, the BERT method demonstrates a remarkable accuracy of 0.95 in the English dataset, whilst the RNN approach gets a noteworthy accuracy of 0.75 in the Bangla dataset. the RF algorithm demonstrates a strong accuracy of 0.94 in the Arabic dataset, whereas the LR method shows a more subtle accuracy of 0.60 in the Hinglish dataset. the language-specific indicators highlight the model's exceptional adaptability, underscoring its vital contribution to promoting a more secure digital environment. the need of using a multilingual strategy becomes apparent, as it effectively deals with the many language subtleties that underpin cyberbullying, therefore making substantial progress in promoting inclusion and flexibility in combating online harassment across various social platforms.

关键词： Radio frequency Cyberbullying Linguistics Market research Real-time systems Natural language processing Communications technology

来源：评论

学校读者我要写书评

暂无评论

Using LLMs and websearch in Order to Perform Fact Checking on Texts Generated by LLMs 19thth

Using LLMs and Websearch in Order to Perform Fact Checkin...

引用

19th international conference on Computer Aided Systems theory, EUROCAST 2024

作者： Sandler, Simone Krauss, Oliver Stöckl, Andreas University of Applied Sciences Upper Austria Campus Hagenberg Softwarepark 11 Hagenberg4232 Austria Advanced Information Systems and Technology Hagenberg Austria Digital Media Department Hagenberg Austria

ISBN: (纸本)9783031829598

Finding out if a given text contains any false information is not an easy task. On large corpora of data, such as the tremendous amount of texts generated by LLMs, fact checking is a prohibitively expensive task. To address this challenge, we propose a novel approach that combines fact checking by LLMs with web search. this method can be applied not only to single sentences by applying a true, false or unknown label. For whole text paragraphs, a 0..1 score representing the truthfulness from the sentence labels is calculated. the process begins by extracting claims from the text, which is done using GPT3. then, these claims are validated, with Google search results being used to supplement the GPT3 results. When validating our method against a corpus of 122 LLM-generated text samples, we achieve an accuracy of 0.79. To compare our work to other approaches, we also applied our fact checking to the FEVER dataset, achieving an accuracy of 0.78. Which is similar than the current best accuracy of 0.79 on the FEVER dataset. this demonstrates the potential of our proposed approach for automated fact checking. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A Finetuned Multimodal Deep Learning Model for Xray Image Diagnosis

A Finetuned Multimodal Deep Learning Model for Xray Image Di...

引用

international conference on Communications, information System and Computer Engineering (CISCE)

作者： Chen Wei Honghao Wang Zhihao Feng Huafeng Mai Zhengzhou University Zhengzhou China University of Melbourne Beijing China Shenzhen Hui Tong International School Shenzhen China University of California San Diego San diego United States

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

Generative conversational AI has shown significant potential in aiding biomedical professionals, yet existing research predominantly targets single-mode textual communication. While multimodal conversational AI has advanced quickly through utilizing vast numbers of image-text pairs available online, these broad-domain vision-language models are still insufficiently refined in their ability to comprehend and discuss biomedical imagery. this article primarily addresses question-answering (QA) for medical imaging data and cancer diagnosis. We constructed a relevant instruction-based QA dataset and performed directive fine-tuning on the Qwen-VL 7B model. thanks to the use of QLora technology, our model can be trained quickly on a Nvidia RTX 4090 graphics card and achieves better results compared to other multimodal models. the experiments showed that the Qwen- VL-7B model has best Rouge-1, Rouge-2, Rouge-L score compared to other models, meaning its highly potential for medical question-answering application.

关键词： Training Measurement Visualization Biological system modeling Graphics processing units X-rays Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共164页 << < 34 35 36 37 38 39 40 41 42 43 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：