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

542 篇 会议
394 篇 期刊文献
4 册 图书

馆藏范围

940 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

597 篇 工学
- 437 篇 计算机科学与技术...
- 376 篇 软件工程
- 132 篇 信息与通信工程
- 69 篇 控制科学与工程
- 54 篇 生物工程
- 43 篇 生物医学工程（可授...
- 38 篇 电气工程
- 31 篇 机械工程
- 26 篇 电子科学与技术（可...
- 22 篇 化学工程与技术
- 16 篇 光学工程
- 14 篇 动力工程及工程热...
367 篇 理学
- 166 篇 物理学
- 134 篇 数学
- 89 篇 生物学
- 65 篇 统计学（可授理学、...
- 44 篇 系统科学
- 25 篇 化学
133 篇 管理学
- 76 篇 图书情报与档案管...
- 52 篇 管理科学与工程(可...
- 29 篇 工商管理
77 篇 医学
- 66 篇 临床医学
- 52 篇 基础医学(可授医学...
- 24 篇 公共卫生与预防医...
- 21 篇 药学(可授医学、理...
49 篇 教育学
- 38 篇 教育学
- 23 篇 心理学(可授教育学...
44 篇 法学
- 42 篇 社会学
20 篇 文学
- 14 篇 外国语言文学
- 13 篇 中国语言文学
17 篇 农学
12 篇 经济学
2 篇 哲学
2 篇 军事学
1 篇 历史学
1 篇 艺术学

主题

80 篇 speech recogniti...
32 篇 hidden markov mo...
27 篇 training
24 篇 speech
22 篇 semantics
21 篇 humans
20 篇 computer science
20 篇 machine translat...
20 篇 decoding
20 篇 machine learning
18 篇 feature extracti...
16 篇 transducers
15 篇 deep learning
14 篇 computer aided l...
14 篇 neural machine t...
13 篇 natural language...
13 篇 natural language...
12 篇 computational li...
11 篇 support vector m...
11 篇 students

机构

43 篇 apptek gmbh aach...
36 篇 human language t...
29 篇 human language t...
18 篇 human language t...
17 篇 institute of res...
16 篇 human language t...
14 篇 trustworthy huma...
13 篇 department of in...
12 篇 department of la...
11 篇 department of co...
11 篇 computer science...
9 篇 department of co...
9 篇 human language t...
9 篇 human language t...
9 篇 hkust human lang...
9 篇 future technolog...
9 篇 school of medici...
8 篇 department of co...
8 篇 health managemen...
8 篇 julius centre fo...

作者

138 篇 ney hermann
62 篇 schlüter ralf
34 篇 wu dekai
33 篇 hermann ney
22 篇 habernal ivan
18 篇 dredze mark
18 篇 hosseinzadeh meh...
17 篇 ralf schlüter
17 篇 pascale fung
17 篇 zhou wei
16 篇 rahmani amir mas...
15 篇 fung pascale
14 篇 gao yingbo
14 篇 michel wilfried
13 篇 ralf schluter
12 篇 yousefpoor moham...
12 篇 zeineldeen moham...
12 篇 badriyya b.al-on...
12 篇 zeyer albert
12 篇 zens richard

语言

913 篇 英文
23 篇 其他
4 篇 中文

检索条件"机构=Department of Computer Science Department of Language and Human Development"

共 940 条记录，以下是701-710 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：

Performance analysis of Neural Networks in combination with n-gram language models

Performance analysis of Neural Networks in combination with ...

引用

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

作者： Ilya Oparin Martin Sundermeyer Hermann Ney Jean-Luc Gauvain LIMSI CNRS Spoken Language Processing Group France Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Germany

Neural Network language models (NNLMs) have recently become an important complement to conventional n-gram language models (LMs) in speech-to-text systems. However, little is known about the behavior of NNLMs. The analysis presented in this paper aims to understand which types of events are better modeled by NNLMs as compared to n-gram LMs, in what cases improvements are most substantial and why this is the case. Such an analysis is important to take further benefit from NNLMs used in combination with conventional n-gram models. The analysis is carried out for different types of neural network (feed-forward and recurrent) LMs. The results showing for which type of events NNLMs provide better probability estimates are validated on two setups that are different in their size and the degree of data homogeneity.

关键词： Artificial neural networks History Analytical models Training data Vocabulary Interpolation

来源：评论

学校读者我要写书评

暂无评论

FloTree: A multi-touch interactive simulation of evolutionary processes 12

FloTree: A multi-touch interactive simulation of evolutionar...

引用

7th ACM International Conference on Interactive Tabletops and Surfaces, ITS 2012

作者： Chua, Kien Chuan Qin, Yongqiang Block, Florian Phillips, Brenda Diamond, Judy Evans, E. Margaret Horn, Michael S. Shen, Chia School of Engineering and Applied Sciences Harvard University Cambridge 02138 United States Department of Computer Science National University of Singapore 117417 Singapore Singapore Department of Computer Science Tsinghua University Beijing 100084 China University of Nebraska State Museum Lincoln NE 68588 United States Center for Human Growth and Development University of Michigan Ann Arbor MI 48109 United States Computer Science and Learning Sciences Northwestern University Evanston 60208 United States

ISBN: (纸本)9781450312097

We present FloTree, a multi-user simulation that illustrates key dynamic processes underlying evolutionary change. Our intention is to create a informal learning environment that links micro-level evolutionary processes to macro-level outcomes of speciation and biodiversity. On a multi-touch table, the simulation represents change from generation to generation in a population of organisms. By placing hands or arms on the surface, visitors can add environmental barriers, thus interrupting the genetic flow between the separated populations. This results in sub-populations that accumulate genetic differences independently over time, sometimes leading to the formation of new species. Learners can morph the result of the simulation into a corresponding phylogenetic tree. The free-form hand and body touch gestures invite creative input from users, encourages social interaction, and provides an opportunity for deep engagement. © 2012 Authors.

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

Lowresource speech recognition with automatically learned sparse inverse covariance matrices

Lowresource speech recognition with automatically learned sp...

引用

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

作者： Weibin Zhang Pascale Fung HKUST Human Language Technology Center Department of Electronic and Computer Engineering University of Science and Technology (HKUST) Hong Kong China

Full covariance acoustic models trained with limited training data generalize poorly to unseen test data due to a large number of free parameters. We propose to use sparse inverse covariance matrices to address this problem. Previous sparse inverse covariance methods never outperformed full covariance methods. We propose a method to automatically drive the structure of inverse covariance matrices to sparse during training. We use a new objective function by adding L1 regularization to the traditional objective function for maximum likelihood estimation. The graphic lasso method for the estimation of a sparse inverse covariance matrix is incorporated into the Expectation Maximization algorithm to learn parameters of HMM using the new objective function. Experimental results show that we only need about 25% of the parameters of the inverse covariance matrices to be nonzero in order to achieve the same performance of a full covariance system. Our proposed system using sparse inverse covariance Gaussians also significantly outperforms a system using full covariance Gaussians trained on limited data.

关键词： Covariance matrix Hidden Markov models Training data Linear programming Sparse matrices Training Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

The RWTH Aachen Machine Translation System for WMT 2012 12

The RWTH Aachen Machine Translation System for WMT 2012

引用

Workshop on Statistical Machine Translation

作者： Matthias Huck Stephan Peitz Markus Freitag Malte Nuhn Hermann Ney Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen Germany

ISBN: (纸本)9781622765928

This paper describes the statistical machine translation (SMT) systems developed at RWTH Aachen University for the translation task of the NAACL 2012 Seventh Workshop on Statistical Machine Translation (WMT 2012). We participated in the evaluation campaign for the French-English and German-English language pairs in both translation directions. Both hierarchical and phrase-based SMT systems are applied. A number of different techniques are evaluated, including an insertion model, different lexical smoothing methods, a discriminative reordering extension for the hierarchical system, reverse translation, and system combination. By application of these methods we achieve considerable improvements over the respective baseline systems.

关键词： machine translation system machine translation Surface mount technology Hierarchical application methods Translations Translation Translation Process smoothing methods Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Phrase-level transduction model with reordering for spoken to written language transformation

Phrase-level transduction model with reordering for spoken t...

引用

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

作者： Ping Xu Pascale Fung Ricky Chan Human Language Technology Center Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China

This paper proposes a first-ever phrase-level transduction model with reordering to transform colloquial speech directly to written-style transcription. This model is capable of performing n-m transductions. Our transduction model is trained from a parallel corpus of verbatim transcription and written-style transcription. Deletions, substitutions, insertions are well represented using this model. Inversion transduction cases can also be identified and represented. We implement our transduction model using weighted finite-state transducers (WFSTs), and integrate it into a WFST-based speech recognition search space to give both verbatim speaking-style and written-style transcriptions. Evaluations of our model on Cantonese speech to standard written Chinese show 11.59% relative Word Error Rate (WER) reduction over interpolated language model between Cantonese and standard Chinese speech, 5.72% relative WER reduction and 14.82% relative Bilingual Evaluation Understudy (BLEU) improvement over the word-level transduction model.

关键词： Speech Hidden Markov models Speech recognition Transducers Standards Decoding Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Tweet recommendation with graph co-ranking

Tweet recommendation with graph co-ranking

引用

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

作者： Yan, Rui Lapata, Mirella Li, Xiaoming Department of Computer Science and Technology Peking University Beijing 100871 China Institute for Language Cognition and Computation University of Edinburgh Edinburgh EH8 9AB United Kingdom State Key Laboratory of Software Development Environment Beihang University Beijing 100083 China

ISBN: (纸本)9781937284244

As one of the most popular micro-blogging services, Twitter attracts millions of users, producing millions of tweets daily. Shared information through this service spreads faster than would have been possible with traditional sources, however the proliferation of user-generation content poses challenges to browsing and finding valuable information. In this paper we propose a graph-theoretic model for tweet recommendation that presents users with items they may have an interest in. Our model ranks tweets and their authors simultaneously using several networks: The social network connecting the users, the network connecting the tweets, and a third network that ties the two together. Tweet and author entities are ranked following a co-ranking algorithm based on the intuition that that there is a mutually reinforcing relationship between tweets and their authors that could be reflected in the rankings. We show that this framework can be parametrized to take into account user preferences, the popularity of tweets and their authors, and diversity. Experimental evaluation on a large dataset shows that our model outperforms competitive approaches by a large margin. © 2012 Association for computational Linguistics.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual language Modeling with Syntactic Reordering for Low-Resource Speech Recognition 12

Cross-Lingual Language Modeling with Syntactic Reordering fo...

引用

Conference on Empirical Methods in Natural language Processing

作者： Ping Xu Pascale Fung Human Language Technology Center Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

ISBN: (纸本)9781622765034

This paper proposes cross-lingual language modeling for transcribing source resource-poor languages and translating them into target resource-rich languages if necessary. Our focus is to improve the speech recognition performance of low-resource languages by leveraging the language model statistics from resource-rich languages. The most challenging work of cross-lingual language modeling is to solve the syntactic discrepancies between the source and target languages. We therefore propose syntactic reordering for cross-lingual language modeling, and present a first result that compares inversion transduction grammar (ITG) reordering constraints to IBM and local constraints in an integrated speech transcription and translation system. Evaluations on resource-poor Cantonese speech transcription and Cantonese to resource-rich Mandarin translation tasks show that our proposed approach improves the system performance significantly, up to 3.4% relative WER reduction in Cantonese transcription and 13.3% relative bilingual evaluation understudy (BLEU) score improvement in Mandarin transcription compared with the system without reordering.

关键词： modelling languages Speech recognition Cantonese syntax language System performance Transcription Genetic Transcription

来源：评论

学校读者我要写书评

暂无评论

Adult learners use both entrenchment and preemption to infer grammatical constraints

Adult learners use both entrenchment and preemption to infer...

引用

IEEE International Conference on development and Learning, ICDL

作者： Jeremy K. Boyd Farrell Ackerman Marta Kutas Center for Research in Language at UCSD 9500 CA USA Department of Linguistics Human Development Program at UCSD Departments of Cognitive Science and Neurosciences Center for Research in Language and the Kavli Institute for Brain and Mind at UCSD

Learners acquire grammatical constraints (e.g., the knowledge that giggle's use in The joke giggled me is ungrammatical) in part through statistical learning. The entrenchment and preemption hypotheses claim that correlated statistics are relevant. This makes it difficult to find unambiguous evidence in favor of one or the other. The present work circumvents this issue by orthogonalizing effects of entrenchment and preemption in a learning task with a novel verb. We find evidence that both entrenchment and preemption have significant independent effects in adult learners.

关键词： Production Motion pictures Semantics Electronic mail Atmospheric measurements Particle measurements Cognition

来源：评论

学校读者我要写书评

暂无评论

Short Utterance Speaker Recognition A research Agenda

Short Utterance Speaker Recognition A research Agenda

引用

International Conference on Systems and Informatics (ICSAI)

作者： Nakhat Fatima Thomas Fang Zheng Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China

Short Utterance Speaker Recognition (SUSR) is an important area of speaker recognition when only small amount of speech data is available for testing and training. We list the most commonly used state-of-the-art methods of speaker recognition and the significance of prosodic speaker recognition. A short survey of SUSR is hereby conducted, highlighting various methodologies when using short utterances to recognize speakers. We also specify future research directions in the field SUSR which, together with modern technologies and the ongoing research in prosodic speaker recognition, can lead to better results in speaker recognition.

关键词： Speaker recognition Speech Hidden Markov models Speech recognition Acoustics Training humans

来源：评论

学校读者我要写书评

暂无评论

Vowel-category based Short Utterance Speaker Recognition

Vowel-category based Short Utterance Speaker Recognition

引用

International Conference on Systems and Informatics (ICSAI)

The impact of Short Utterances in Speaker Recognition is of significant importance. Despite the advancements in short utterance speaker recognition (SUSR), text dependence and the role of phonemes in carrying speaker information needs further investigation. This paper presents a novel method of using vowel categories for SUSR. We define Vowel Categories (VC's) considering Chinese and English languages. After recognition and extraction of phonemes, the obtained vowels are divided into VC's, which are then used to develop Universal Background VC Models (UBVCM) for each VC. Conventional GMM-UBM system is used for training and testing. The proposed categories give minimum EERs of 13.76%, 14.03% and 16.18% for 3, 2 and 1 second respectively. Experimental results show that in text dependent SUSR, significant speaker-specific information is present at phoneme level. The similar properties of phonemes can be used such that accurate speech recognition is not required, rather Phoneme Categories can be used effectively for SUSR. Also, it is shown that vowels contain large amount of speaker information, which remains undisturbed when VC are employed.

关键词： Speaker recognition Speech Speech recognition Training Testing Feature extraction Hidden Markov models

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94页 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：