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

329 篇 会议
129 篇 期刊文献

馆藏范围

458 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

322 篇 工学
- 243 篇 计算机科学与技术...
- 211 篇 软件工程
- 99 篇 信息与通信工程
- 27 篇 生物工程
- 19 篇 控制科学与工程
- 17 篇 电气工程
- 17 篇 化学工程与技术
- 14 篇 电子科学与技术（可...
- 13 篇 仪器科学与技术
- 11 篇 生物医学工程（可授...
- 7 篇 机械工程
- 7 篇 建筑学
- 6 篇 安全科学与工程
- 5 篇 土木工程
- 5 篇 农业工程
171 篇 理学
- 122 篇 物理学
- 59 篇 数学
- 32 篇 生物学
- 22 篇 统计学（可授理学、...
- 17 篇 化学
- 10 篇 系统科学
78 篇 管理学
- 69 篇 图书情报与档案管...
- 6 篇 管理科学与工程(可...
15 篇 医学
- 13 篇 基础医学(可授医学...
- 13 篇 临床医学
- 8 篇 药学(可授医学、理...
- 6 篇 公共卫生与预防医...
9 篇 法学
- 7 篇 社会学
8 篇 文学
- 6 篇 中国语言文学
- 5 篇 外国语言文学
6 篇 教育学
5 篇 农学
1 篇 经济学

主题

47 篇 speech recogniti...
31 篇 speech
30 篇 training
18 篇 acoustics
14 篇 machine translat...
13 篇 decoding
12 篇 social networkin...
12 篇 speaker recognit...
11 篇 hidden markov mo...
11 篇 computational mo...
11 篇 semantics
10 篇 conferences
9 篇 speech processin...
9 篇 computational li...
9 篇 feature extracti...
9 篇 embeddings
8 篇 training data
8 篇 natural language...
8 篇 pipelines
7 篇 lattices

机构

88 篇 human language t...
55 篇 human language t...
43 篇 center for langu...
21 篇 center for langu...
20 篇 human language t...
20 篇 human language t...
18 篇 center for langu...
15 篇 human language t...
13 篇 center for langu...
12 篇 human language t...
11 篇 human language t...
10 篇 johns hopkins un...
9 篇 johns hopkins un...
8 篇 human language t...
7 篇 human language t...
7 篇 department of co...
7 篇 xiaomi corp.
6 篇 computer and inf...
6 篇 xiaomi corporati...
6 篇 center for langu...

作者

64 篇 dredze mark
50 篇 khudanpur sanjee...
43 篇 van durme benjam...
30 篇 dehak najim
27 篇 sanjeev khudanpu...
21 篇 post matt
20 篇 mcnamee paul
20 篇 hermansky hynek
20 篇 callison-burch c...
19 篇 villalba jesús
18 篇 povey daniel
16 篇 duh kevin
16 篇 mayfield james
15 篇 zelasko piotr
15 篇 daniel povey
15 篇 watanabe shinji
14 篇 wiesner matthew
14 篇 andrews nicholas
13 篇 paul michael j.
13 篇 mccree alan

语言

443 篇 英文
15 篇 其他

检索条件"机构=Human Language Technology Center of Excellence and Center for Language and Speech Processing"

共 458 条记录，以下是361-370 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：

Efficient discriminative training of long-span language models

Efficient discriminative training of long-span language mode...

引用

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Ariya Rastrow Mark Dredze Sanjeev Khudanpur Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

Long-span language models, such as those involving syntactic dependencies, produce more coherent text than their n-gram counterparts. However, evaluating the large number of sentence-hypotheses in a packed representation such as an ASR lattice is intractable under such long-span models both during decoding and discriminative training. The accepted compromise is to rescore only the N-best hypotheses in the lattice using the long-span LM. We present discriminative hill climbing, an efficient and effective discriminative training procedure for long-span LMs based on a hill climbing rescoring algorithm [1]. We empirically demonstrate significant computational savings as well as error-rate reduction over N-best training methods in a state of the art ASR system for Broadcast News transcription.

关键词： Training Lattices Acoustics Syntactics speech Feature extraction Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Efficient spoken term discovery using randomized algorithms

Efficient spoken term discovery using randomized algorithms

引用

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Aren Jansen Benjamin Van Durme Human Language Technology Center of Excellence & The Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

Spoken term discovery is the task of automatically identifying words and phrases in speech data by searching for long repeated acoustic patterns. Initial solutions relied on exhaustive dynamic time warping-based searches across the entire similarity matrix, a method whose scalability is ultimately limited by the O(n 2 ) nature of the search space. Recent strategies have attempted to improve search efficiency by using either unsupervised or mismatched-language acoustic models to reduce the complexity of the feature representation. Taking a completely different approach, this paper investigates the use of randomized algorithms that operate directly on the raw acoustic features to produce sparse approximate similarity matrices in O(n) space and O(n log n) time. We demonstrate these techniques facilitate spoken term discovery performance capable of outperforming a model-based strategy in the zero resource setting.

关键词： Approximation methods Acoustics Sparse matrices speech Approximation algorithms Vectors Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Adapting n-gram maximum entropy language models with conditional entropy regularization

Adapting n-gram maximum entropy language models with conditi...

引用

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Ariya Rastrow Mark Dredze Sanjeev Khudanpur Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

Accurate estimates of language model parameters are critical for building quality text generation systems, such as automatic speech recognition. However, text training data for a domain of interest is often unavailable. Instead, we use semi-supervised model adaptation; parameters are estimated using both unlabeled in-domain data (raw speech audio) and labeled out of domain data (text.) In this work, we present a new semi-supervised language model adaptation procedure for Maximum Entropy models with n-gram features. We augment the conventional maximum likelihood training criterion on out-of-domain text data with an additional term to minimize conditional entropy on in-domain audio. Additionally, we demonstrate how to compute conditional entropy efficiently on speech lattices using first- and second-order expectation semirings. We demonstrate improvements in terms of word error rate over other adaptation techniques when adapting a maximum entropy language model from broadcast news to MIT lectures.

关键词： Entropy Adaptation models Training Lattices speech Data models Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Using large monolingual and bilingual corpora to improve coordination disambiguation

Using large monolingual and bilingual corpora to improve coo...

引用

49th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-HLT 2011

作者： Bergsma, Shane Yarowsky, David Church, Kenneth Deptartment of Computer Science Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781932432879

Resolving coordination ambiguity is a classic hard problem. This paper looks at coordination disambiguation in complex noun phrases (NPs). Parsers trained on the Penn Treebank are reporting impressive numbers these days, but they don't do very well on this problem (79%). We explore systems trained using three types of corpora: (1) annotated (e.g. the Penn Treebank), (2) bitexts (e.g. Europarl), and (3) unannotated monolingual (e.g. Google N-grams). Size matters: (1) is a million words, (2) is potentially billions of words and (3) is potentially trillions of words. The unannotated monolingual data is helpful when the ambiguity can be resolved through associations among the lexical items. The bilingual data is helpful when the ambiguity can be resolved by the order of words in the translation. We train separate classifiers with monolingual and bilingual features and iteratively improve them via co-training. The co-trained classifier achieves close to 96% accuracy on Treebank data and makes 20% fewer errors than a supervised system trained with Treebank annotations. © 2011 Association for Computational Linguistics.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Judging grammaticality with tree substitution grammar derivations

Judging grammaticality with tree substitution grammar deriva...

引用

49th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-HLT 2011

作者： Post, Matt Human Language Technology Center of Excellence Johns Hopkins University Baltimore MD 21211 United States

ISBN: (纸本)9781932432886

In this paper, we show that local features computed from the derivations of tree substitution grammars - such as the identify of particular fragments, and a count of large and small fragments-are useful in binary grammatical classification tasks. Such features outperform n-gram features and various model scores by a wide margin. Although they fall short of the performance of the hand-crafted feature set of Charniak and Johnson (2005) developed for parse tree reranking, they do so with an order of magnitude fewer features. Furthermore, since the TSGs employed are learned in a Bayesian setting, the use of their derivations can be viewed as the automatic discovery of tree patterns useful for classification. On the BLLIP dataset, we achieve an accuracy of 89.9% in discriminating between grammatical text and samples from an n-gram language model. © 2011 Association for Computational Linguistics.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Learning bilingual lexicons using the visual similarity of labeled web images

Learning bilingual lexicons using the visual similarity of l...

引用

22nd International Joint Conference on Artificial Intelligence, IJCAI 2011

作者： Bergsma, Shane Van Durme, Benjamin Department of Computer Science Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9781577355120

Speakers of many different languages use the Internet. A common activity among these users is uploading images and associating these images with words (in their own language) as captions, filenames, or surrounding text. We use these explicit, monolingual, image-to-word connections to successfully learn implicit, bilingual, word-to-word translations. Bilingual pairs of words are proposed as translations if their corresponding images have similar visual features. We generate bilingual lexicons in 15 language pairs, focusing on words that have been automatically identified as physical objects. The use of visual similarity substantially improves performance over standard approaches based on string similarity: for generated lexicons with 1000 translations, including visual information leads to an absolute improvement in accuracy of 8-12% over string edit distance alone.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Exploiting temporal coherence in speech for data-driven feature extraction

Exploiting temporal coherence in speech for data-driven feat...

引用

Annual Conference on Information Sciences and Systems

作者： Carlin, Michael A. Elhilali, Mounya Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States Human Language Technology Center of Excellence Johns Hopkins University Baltimore MD 21218 United States Dept. of Electrical and Computer Engineering Johns Hopkins University Baltimore MD 21218 United States

ISBN: (纸本)9781424498475

It is well known that speech sounds evolve at multiple timescales over the course of tens to hundreds of milliseconds. Such temporal modulations are crucial for speech perception and are believed to directly influence the underlying code for representing acoustic stimuli. The present work seeks to explicitly quantify this relationship using the principle of temporal coherence. Here we show that by constraining the outputs of model linear neurons to be highly correlated over timescales relevant to speech, we observe the emergence of neural response fields that are bandpass, localized, and reflective of the rich spectro-temporal structure present in speech. The emergent response fields also appear to share qualitative similarities those observed in auditory neurophysiology. Importantly, learning is accomplished using unlabeled speech data, and the emergent neural properties well-characterize the spectro-temporal statistics of the input. We analyze the characteristics and coverage of ensembles of learned response fields for a variety of timescales, and suggest uses of such a coherence learning framework for common speech tasks. © 2011 IEEE.

关键词： speech

来源：评论

学校读者我要写书评

暂无评论

MULTILAYER PERCEPTRON WITH SPARSE HIDDEN OUTPUTS FOR PHONEME RECOGNITION

MULTILAYER PERCEPTRON WITH SPARSE HIDDEN OUTPUTS FOR PHONEME...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： G.S.V.S. Sivaram Hynek Hermansky Department of Electrical & Computer Engineering Center of Language and Speech Processing Human Language Technology Center of Excellence Johns Hopkins University USA

This paper introduces the sparse multilayer perceptron (SMLP) which learns the transformation from the inputs to the targets as in multilayer perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the cross-entropy cost and learning the parameters of the network to minimize the joint cost. On the TIMIT phoneme recognition task, the SMLP based system trained using perceptual linear prediction (PLP) features performs better than the conventional MLP based system. Furthermore, their combination yields a phoneme error rate of 21.2percent, a relative improvement of 6.2percent over the baseline.

关键词： Hidden Markov models Neurons Training Cost function speech speech processing Acoustics

来源：评论

学校读者我要写书评

暂无评论

NADA: A robust system for non-referential pronoun detection

引用

8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011

作者： Bergsma, Shane Yarowsky, David Dept. of Computer Science Human Language Technology Center of Excellence Johns Hopkins University United States

ISBN: (纸本)9783642259166

We present: the Non-Anaphoric Detection Algorithm. is a novel, publicly-available program that accurately distinguishes between the referential and non-referential pronoun it in raw English text. Like recent state-of-the-art approaches, uses very large-scale web features, but makes these features practical by compressing the counts so they can fit into computer memory. therefore operates as a fast, stand-alone system. also improves over previous web-scale systems by considering the entire sentence, rather than narrow context windows, via long-distance lexical features. very substantially outperforms other state-of-the-art systems in non-referential detection accuracy. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Joint training of dependency parsing filters through latent support vector machines

Joint training of dependency parsing filters through latent ...

引用

49th Annual Meeting of the Association for Computational Linguistics: human language Technologies, ACL-HLT 2011

作者： Cherry, Colin Bergsma, Shane Institute for Information Technology National Research Council Canada Canada Center for Language and Speech Processing Johns Hopkins University United States

ISBN: (纸本)9781932432886

Graph-based dependency parsing can be sped up significantly if implausible arcs are eliminated from the search-space before parsing begins. State-of-the-art methods for arc filtering use separate classifiers to make pointwise decisions about the tree;they label tokens with roles such as root, leaf, or attaches-to-the-left, and then filter arcs accordingly. Because these classifiers overlap substantially in their filtering consequences, we propose to train them jointly, so that each classifier can focus on the gaps of the others. We integrate the various pointwise decisions as latent variables in a single arc-level SVM classifier. This novel framework allows us to combine nine pointwise filters, and adjust their sensitivity using a shared threshold based on arc length. Our system filters 32% more arcs than the independently-trained classifiers, without reducing filtering speed. This leads to faster parsing with no reduction in accuracy. © 2011 Association for Computational Linguistics.

关键词： Support vector machines

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46页 << < 33 34 35 36 37 38 39 40 41 42 > >>

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：