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

530 篇 会议
298 篇 期刊文献
3 册 图书

馆藏范围

831 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

521 篇 工学
- 390 篇 计算机科学与技术...
- 338 篇 软件工程
- 142 篇 信息与通信工程
- 56 篇 生物工程
- 45 篇 控制科学与工程
- 40 篇 电子科学与技术（可...
- 35 篇 仪器科学与技术
- 33 篇 化学工程与技术
- 30 篇 电气工程
- 21 篇 生物医学工程（可授...
- 16 篇 机械工程
- 16 篇 光学工程
- 7 篇 建筑学
- 6 篇 材料科学与工程（可...
292 篇 理学
- 167 篇 物理学
- 118 篇 数学
- 63 篇 生物学
- 55 篇 统计学（可授理学、...
- 31 篇 化学
- 18 篇 系统科学
122 篇 管理学
- 79 篇 图书情报与档案管...
- 45 篇 管理科学与工程(可...
- 15 篇 工商管理
17 篇 医学
- 13 篇 临床医学
- 10 篇 基础医学(可授医学...
- 8 篇 药学(可授医学、理...
15 篇 法学
- 13 篇 社会学
12 篇 文学
- 8 篇 中国语言文学
- 8 篇 外国语言文学
11 篇 农学
- 7 篇 作物学
4 篇 教育学
3 篇 经济学
3 篇 艺术学
1 篇 军事学

主题

77 篇 speech recogniti...
74 篇 training
50 篇 acoustics
46 篇 speech processin...
44 篇 speech
33 篇 hidden markov mo...
31 篇 signal processin...
29 篇 feature extracti...
26 篇 decoding
23 篇 speech enhanceme...
21 篇 computational mo...
20 篇 speech synthesis
20 篇 linguistics
19 篇 predictive model...
18 篇 natural language...
18 篇 data models
17 篇 neural networks
16 篇 accuracy
15 篇 conferences
15 篇 training data

机构

71 篇 national enginee...
55 篇 school of comput...
47 篇 audio speech and...
42 篇 beijing engineer...
27 篇 department of co...
26 篇 center for langu...
21 篇 department of co...
18 篇 mainlp center fo...
18 篇 department of co...
15 篇 audio speech and...
14 篇 iflytek research
14 篇 national enginee...
12 篇 munich
11 篇 department of co...
10 篇 center for infor...
10 篇 ict cluster sing...
10 篇 audio speech and...
9 篇 center for infor...
9 篇 department of co...
9 篇 center for speec...

作者

71 篇 lei xie
54 篇 ling zhen-hua
37 篇 huang heyan
32 篇 ai yang
23 篇 plank barbara
22 篇 zhen-hua ling
19 篇 yang ai
18 篇 zheng thomas fan...
18 篇 yarowsky david
18 篇 thomas fang zhen...
17 篇 wang dong
17 篇 heyan huang
17 篇 khudanpur sanjee...
16 篇 lu ye-xin
15 篇 pengcheng guo
15 篇 gu jia-chen
15 篇 van der goot rob
14 篇 du jun
14 篇 mao xian-ling
14 篇 xie lei

语言

699 篇 英文
127 篇 其他
12 篇 中文

检索条件"机构=Center for Language and Speech Processing and Computer Science"

共 831 条记录，以下是751-760 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：

Paragraph-level alignment of an english-spanish parallel corpus of fiction texts using bilingual dictionaries

引用

9th International Conference on Text, speech and Dialogue, TSD 2006

作者： Gelbukh, Alexander Sidorov, Grigori Vera-Félix, José Ángel Natural Language and Text Processing Laboratory Center for Research in Computer Science National Polytechnic Institute Av. Juan Dios Batiz s/n Zacatenco 07738 Mexico City Mexico

ISBN: (纸本)3540390901

Aligned parallel corpora are very important linguistic resources useful in many text processing tasks such as machine translation, word sense disambiguation, dictionary compilation, etc. Nevertheless, there are few available linguistic resources of this type, especially for fiction texts, due to the difficulties in collecting the texts and high cost of manual alignment. In this paper, we describe an automatically aligned English-Spanish parallel corpus of fiction texts and evaluate our method of alignment that uses linguistic data-namely, on the usage of existing bilingual dictionaries-to calculate word similarity. The method is based on the simple idea: if a meaningful word is present in the source text then one of its dictionary translations should be present in the target text. Experimental results of alignment at paragraph level are described. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Generative content models for structural analysis of medical abstracts

Generative content models for structural analysis of medical...

引用

HLT-NAACL 2006 Workshop on Linking Natural language processing and Biology: Towards Deeper Biological Literature Analysis, BioNLP 2006

作者： Lin, Jimmy Karakos, Damianos Demner-Fushman, Dina Khudanpur, Sanjeev College of Information Studies University of Maryland College ParkMD20742 United States Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States

The ability to accurately model the content structure of text is important for many natural language processing applications. This paper describes experiments with generative models for analyzing the discourse structure of medical abstracts, which generally follow the pattern of "introduction", "methods", "results", and "conclusions". We demonstrate that Hidden Markov Models are capable of accurately capturing the structure of such texts, and can achieve classification accuracy comparable to that of discriminative techniques. In addition, generative approaches provide advantages that may make them preferable to discriminative techniques such as Support Vector Machines under certain conditions. Our work makes two contributions: at the application level, we report good performance on an interesting task in an important domain;more generally, our results contribute to an ongoing discussion regarding the tradeoffs between generative and discriminative techniques. © 2006 Association for Computational Linguistics.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Improving rapid unsupervised speaker adaptation based on HMM-sufficient statistics in noisy environments using multi-template models

Improving rapid unsupervised speaker adaptation based on HMM...

引用

作者： Gomez, Randy Lee, Akinobu Toda, Tomoki Saruwatari, Hiroshi Shikano, Kiyohiro Nara Institute of Science and Technology Ikoma-shi 630-0192 Japan Nagoya Institute of Technology Nagoya-shi 466-8555 Japan Speech and Acoustics Laboratory Nara Institute of Science and Technology Japan Department of Computer Science and Engineering Nagoya Institute of Technology Japan Information Processing Society of Japan Japan Acoustical Society of Japan Japan Graduate School of Information Science Nara Institute of Science and Technology Japan ATR Spoken Language Communication Research Laboratories Japan ISCA VR Society of Japan Japan Japan International Speech Communication Society

This paper describes the method of using multi-template unsupervised speaker adaptation based on HMM-Sufficient Statistics to push up the adaptation performance while keeping adaptation time within few seconds with just one arbitrary utterance. This adaptation scheme is mainly composed of two processes. The first part is done offline which involves the training of multiple class-dependent acoustic models and the creation of speakers' HMM-Sufficient Statistics based on gender and age. The second part is performed online where adaptation begins using the single utterance of a test speaker. From this utterance, the system will classify the speaker's class and consequently select the N-best neighbor speakers close to the utterance using Gaussian Mixture Models (GMM). The classified speakers' class template model is then adopted as a base model. From this template model, the adapted model is rapidly constructed using the N-best neighbor speakers' HMM-Sufficient Statistics. Experiments in noisy environment conditions with 20 dB, 15 dB and 10 dB SNR office, crowd, booth, and car noise are performed. The proposed multi-template method achieved 89.5% word accuracy rate compared with 88.1% of the conventional single-template method, while the baseline recognition rate without adaptation is 86.4%. Moreover, experiments using Vocal Tract Length Normalization (VTLN) and supervised Maximum Likelihood Linear Regression (MLLR) are also compared. Copyright © 2006 The Institute of Electronics, Information and Communication Engineers.

关键词： Acoustic wave effects

来源：评论

学校读者我要写书评

暂无评论

Gesture Spotting in Low-Quality Video with Features Based on Curvature Scale Space

Gesture Spotting in Low-Quality Video with Features Based on...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Myung-Cheol Roh B. Christmas J. Kittler Seong-Whan Lee Department of Computer Science and Engineering Korea University Seoul South Korea Center for Vision Speechand Signal Processing University of Surrey Guildford UK

Player's gesture and action spotting in sports video is a key task in automatic analysis of the video material at a high level. In many sports views, the camera covers a large part of the sports arena, so that the area of player's region is small, and has large motion. These make the determination of the player's gestures and actions a challenging task. To overcome these problems, we propose a method based on curvature scale space templates of the player's silhouette. The use of curvature scale space makes the method robust to noise and our method is robust to significant shape corruption of a part of player's silhouette. We also propose a new recognition method which is robust to noisy sequence of posture and needs only a small amount of training data, which is essential characteristic for many practical applications

关键词： Noise robustness Cameras computer science speech analysis Noise shaping Shape Surveillance Face recognition speech processing Video signal processing

来源：评论

学校读者我要写书评

暂无评论

The AT&T spoken language understanding system

The AT&T spoken language understanding system

引用

作者： Gupta, Narendra Tur, Gokhan Hakkani-Tür, Dilek Bangalore, Srinivas Riccardi, Giuseppe Gilbert, Mazin IEEE AT and T Labs.-Research Florham Park NJ 07932 United States Computer Science Department University of Trento Trento Italy AT and T VoiceTone Service ACL ISCA AT and T Laboratories-Research Florham Park NJ Association for Computational Linguistics Voice Enabled Services Laboratory AT and T Laboratories-Research Florham Park NJ AT and T Labs.-Research Computer Science Department University of Trente Trento Italy New York Academy of Science Natural Language Processing Division AT and T Labs. Research IEEE Speech Technical Committee CAIP Industrial Board Rutgers University

Spoken language understanding (SLU) aims at extracting meaning from natural language speech. Over the past decade, a variety of practical goal-oriented spoken dialog systems have been built for limited domains. SLU in these systems ranges from understanding predetermined phrases through fixed grammars, extracting some predefined named entities, extracting users' intents for call classification, to combinations of users' intents and named entities. In this paper, we present the SLU system of VoiceTone® (a service provided by AT&T where AT&T develops, deploys and hosts spoken dialog applications for enterprise customers). The SLU system includes extracting both intents and the named entities from the users' utterances. For intent determination, we use statistical classifiers trained from labeled data, and for named entity extraction we use rule-based fixed grammars. The focus of our work is to exploit data and to use machine learning techniques to create scalable SLU systems which can be quickly deployed for new domains with minimal human intervention. These objectives are achieved by 1) using the predicate-argument representation of semantic content of an utterance;2) extending statistical classifiers to seamlessly integrate hand crafted classification rules with the rules learned from data;and 3) developing an active learning framework to minimize the human labeling effort for quickly building the classifier models and adapting them to changes. We present an evaluation of this system using two deployed applications of VoiceTone®. © 2006 IEEE.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

Context-based morphological disambiguation with random fields 05

Context-based morphological disambiguation with random field...

引用

Human language Technology Conference and Conference on Empirical Methods in Natural language processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT

作者： Smith, Noah A. Smith, David A. Tromble, Roy W. Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

Finite-state approaches have been highly successful at describing the morphological processes of many languages. Such approaches have largely focused on modeling the phone- or character-level processes that generate candidate lexical types, rather than tokens in context. For the full analysis of words in context, disambiguation is also required (Hakkani-Tür et al., 2000;Hajič et al., 2001). In this paper, we apply a novel source-channel model to the problem of morphological disambiguation (segmentation into morphemes, lemmatization, and POS tagging) for concatenative, templatic, and inflectional languages. The channel model exploits an existing morphological dictionary, constraining each word's analysis to be linguistically valid. The source model is a factored, conditionally-estimated random field (Lafferty et al., 2001) that learns to disambiguate the full sentence by modeling local contexts. Compared with baseline state-of-the-art methods, our method achieves statistically significant error rate reductions on Korean, Arabic, and Czech, for various training set sizes and accuracy measures. © 2005 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Compiling comp ling: Practical weighted dynamic programming and the Dyna language

Compiling comp ling: Practical weighted dynamic programming ...

引用

作者： Eisner, Jason Goldlust, Eric Smith, Noah A. Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

Weighted deduction with aggregation is a powerful theoretical formalism that encompasses many NLP algorithms. This paper proposes a declarative specification language, Dyna;gives general agenda-based algorithms for computing weights and gradients;briefly discusses Dyna-to-Dyna program transformations;and shows that a first implementation of a Dyna-to-C++ compiler produces code that is efficient enough for real NLP research, though still several times slower than hand-crafted code. © 2005 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Contrastive estimation: Training log-linear models on unlabeled data

Contrastive estimation: Training log-linear models on unlabe...

引用

43rd Annual Meeting of the Association for Computational Linguistics, ACL-05

作者： Smith, Noah A. Eisner, Jason Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

ISBN: (纸本)1932432515

Conditional random fields (Lafferty et al., 2001) are quite effective at sequence labeling tasks like shallow parsing (Sha and Pereira, 2003) and namedentity extraction (McCallum and Li, 2003). CRFs are log-linear, allowing the incorporation of arbitrary features into the model. To train on unlabeled data, we require unsupervised estimation methods for log-linear models;few exist. We describe a novel approach, contrastive estimation. We show that the new technique can be intuitively understood as exploiting implicit negative evidence and is computationally efficient. Applied to a sequence labeling problem-POS tagging given a tagging dictionary and unlabeled text-contrastive estimation outperforms EM (with the same feature set), is more robust to degradations of the dictionary, and can largely recover by modeling additional features. © 2005 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Parsing with soft and hard constraints on dependency length 9

Parsing with soft and hard constraints on dependency length

引用

9th International Workshop on Parsing Technologies, IWPT 2005

作者： Eisner, Jason Smith, Noah A. Department of Computer Science Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States

In lexicalized phrase-structure or dependency parses, a word's modifiers tend to fall near it in the string. We show that a crude way to use dependency length as a parsing feature can substantially improve parsing speed and accuracy in English and Chinese, with more mixed results on German. We then show similar improvements by imposing hard bounds on dependency length and (additionally) modeling the resulting sequence of parse fragments. This simple "vine grammar" formalism has only finite-state power, but a context-free parameterization with some extra parameters for stringing fragments together. We exhibit a linear-time chart parsing algorithm with a low grammar constant. © 2005 Association for Computational Linguistics

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

Using random forests in the structured language model

Using random forests in the structured language model

引用

18th Annual Conference on Neural Information processing Systems, NIPS 2004

作者： Xu, Peng Jelinek, Frederick Department of Electrical and Computer Engineering Center for Language and Speech Processing Johns Hopkins University United States

ISBN: (纸本)0262195348

In this paper, we explore the use of Random Forests (RFs) in the structured language model (SLM), which uses rich syntactic information in predicting the next word based on words already seen. The goal in this work is to construct RFs by randomly growing Decision Trees (DTs) using syntactic information and investigate the performance of the SLM modeled by the RFs in automatic speech recognition. RFs, which were originally developed as classifiers, are a combination of decision tree classifiers. Each tree is grown based on random training data sampled independently and with the same distribution for all trees in the forest, and a random selection of possible questions at each node of the decision tree. Our approach extends the original idea of RFs to deal with the data sparseness problem encountered in language modeling. RFs have been studied in the context of n-gram language modeling and have been shown to generalize well to unseen data. We show in this paper that RFs using syntactic information can also achieve better performance in both perplexity (PPL) and word error rate (WER) in a large vocabulary speech recognition system, compared to a baseline that uses Kneser-Ney smoothing.

关键词： Decision trees

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84页 << < 72 73 74 75 76 77 78 79 80 81 > >>

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：