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

292 篇 会议
143 篇 期刊文献
3 册 图书

馆藏范围

438 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

294 篇 工学
- 218 篇 计算机科学与技术...
- 188 篇 软件工程
- 80 篇 信息与通信工程
- 32 篇 生物工程
- 21 篇 控制科学与工程
- 17 篇 仪器科学与技术
- 16 篇 生物医学工程（可授...
- 15 篇 化学工程与技术
- 13 篇 电子科学与技术（可...
- 9 篇 机械工程
- 8 篇 电气工程
- 6 篇 光学工程
- 5 篇 材料科学与工程（可...
- 4 篇 动力工程及工程热...
169 篇 理学
- 95 篇 物理学
- 68 篇 数学
- 38 篇 统计学（可授理学、...
- 37 篇 生物学
- 15 篇 化学
- 13 篇 系统科学
72 篇 管理学
- 51 篇 图书情报与档案管...
- 21 篇 管理科学与工程(可...
- 7 篇 工商管理
12 篇 医学
- 11 篇 临床医学
- 8 篇 基础医学(可授医学...
- 7 篇 药学(可授医学、理...
10 篇 文学
- 8 篇 外国语言文学
- 7 篇 中国语言文学
9 篇 法学
- 8 篇 社会学
7 篇 农学
- 5 篇 作物学
2 篇 经济学
2 篇 教育学
1 篇 军事学
1 篇 艺术学

主题

49 篇 speech recogniti...
24 篇 speech
21 篇 hidden markov mo...
21 篇 training
19 篇 speech processin...
14 篇 acoustics
13 篇 decoding
13 篇 natural language...
12 篇 computational mo...
11 篇 signal processin...
9 篇 computational li...
9 篇 databases
9 篇 feature extracti...
8 篇 natural language...
8 篇 syntactics
8 篇 automatic speech...
7 篇 training data
7 篇 testing
7 篇 speaker recognit...
6 篇 machine translat...

机构

27 篇 department of co...
24 篇 center for langu...
21 篇 department of co...
18 篇 department of co...
16 篇 mainlp center fo...
12 篇 munich
11 篇 department of co...
9 篇 center for infor...
9 篇 department of co...
9 篇 center for speec...
7 篇 department of co...
7 篇 human language t...
7 篇 department of el...
7 篇 center for langu...
7 篇 center for langu...
6 篇 center for speec...
6 篇 center for infor...
6 篇 speechlab depart...
6 篇 center for langu...
6 篇 national enginee...

作者

21 篇 plank barbara
18 篇 zheng thomas fan...
18 篇 yarowsky david
17 篇 thomas fang zhen...
15 篇 van der goot rob
14 篇 khudanpur sanjee...
12 篇 wang dong
12 篇 sanjeev khudanpu...
11 篇 callison-burch c...
11 篇 eisner jason
9 篇 schütze hinrich
9 篇 lei xie
9 篇 koehn philipp
9 篇 cotterell ryan
8 篇 du xiaojiang
8 篇 smith noah a.
8 篇 zhu liehuang
8 篇 watanabe shinji
7 篇 li zhifei
7 篇 dredze mark

语言

424 篇 英文
11 篇 其他
5 篇 中文

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

共 438 条记录，以下是311-320 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：

Improving Chinese POS Tagging with Dependency Parsing 5

Improving Chinese POS Tagging with Dependency Parsing

引用

5th International Joint Conference on Natural language processing, IJCNLP 2011

作者： Li, Zhenghua Che, Wanxiang Liu, Ting Research Center for Social Computing and Information Retrieval MOE-Microsoft Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology Harbin Institute of Technology China

ISBN: (纸本)9789744665645

Recent research usually models POS tagging as a sequential labeling problem, in which only local context features can be used. Due to the lack of morphological inflections, many tagging ambiguities in Chinese are difficult to handle unless consulting larger contexts. In this paper, we try to improve Chinese POS tagging by using long-distance dependencies produced by a statistical dependency parser. Experimental results show that, despite error propagation, the syntactic features can significantly improve the tagging accuracy from 93.88% to 94.41% (p -5). Detailed analysis shows that these features are helpful for ambiguous pairs like {NN,VV} and {DEC,DEG}. © 2011 AFNLP

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Word Sense Disambiguation Corpora Acquisition via Confirmation Code 5

Word Sense Disambiguation Corpora Acquisition via Confirmati...

引用

5th International Joint Conference on Natural language processing, IJCNLP 2011

作者： Che, Wanxiang Liu, Ting Research Center for Social Computing and Information Retrieval MOE-Microsoft Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology Harbin Institute of Technology China

ISBN: (纸本)9789744665645

Word Sense Disambiguation (WSD) is one of the fundamental natural language processing tasks. However, lack of training corpora is a bottleneck to construct a high accurate all-words WSD system. Annotating a large-scale corpus by experts costs enormous time and financial resources. Human Computation is a novel idea for integrating human resources behind the Web, which has been wasted, to solve practical problems that are difficult for computers. Based on human computation, we design a confirmation code system, which can not only distinguish between human beings and computers (the function of normal confirmation code system), but also annotate WSD corpora. The preliminary experimental result shows that the proposed method can annotate large-scale and high-quality WSD corpora within a short time. To the best of our knowledge, this is the first attempt to use confirmation code in natural language processing for corpora acquisition. © 2011 AFNLP

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Generating Chinese Named Entity Data from a Parallel Corpus 5

Generating Chinese Named Entity Data from a Parallel Corpus

引用

5th International Joint Conference on Natural language processing, IJCNLP 2011

作者： Fu, Ruiji Qin, Bing Liu, Ting Research Center for Social Computing and Information Retrieval MOE-Microsoft Key Laboratory of Natural Language Processing and Speech School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (纸本)9789744665645

Annotating Named Entity Recognition (NER) training corpora is a costly process but necessary for supervised NER systems. This paper presents an approach to generate large-scale Chinese NER training data from an English-Chinese discourse level aligned parallel corpus. Difficulty of NER is different among languages due to their unique features. For example, the performance of English NER systems is usually higher than the Chinese ones on average. In our method, we first employ a high performance NER system on one side of a bilingual corpus. And then, we project the NE labels to the other side according to the word level alignment. At last, we select high-quality labeled sentences using different strategies and generate an NER training corpus. In our experiments, we generate a Chinese NER corpus with 167,100 sentences through an English-Chinese parallel corpus. The system trained on the automatically generated corpus attains a comparable result with the one trained on the manually-annotated corpus. Further experiments show that the NER performance is significantly improved on two different evaluation sets by using the generated training data as an additional corpus to the manually-labeled data. © 2011 AFNLP

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Randomized maximum entropy language models

Randomized maximum entropy language models

引用

2011 IEEE Workshop on Automatic speech Recognition and Understanding, ASRU 2011

作者： Xu, Puyang Khudanpur, Sanjeev Gunawardana, Asela Department of Electrical and Computer Engineering Center of Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States Microsoft Research Redmond WA 98052 United States

ISBN: (纸本)9781467303675

We address the memory problem of maximum entropy language models(MELM) with very large feature sets. Randomized techniques are employed to remove all large, exact data structures in MELM implementations. To avoid the dictionary structure that maps each feature to its corresponding weight, the feature hashing trick [1] [2] can be used. We also replace the explicit storage of features with a Bloom filter. We show with extensive experiments that false positive errors of Bloom filters and random hash collisions do not degrade model performance. Both perplexity and WER improvements are demonstrated by building MELM that would otherwise be prohibitively large to estimate or store. © 2011 IEEE.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Efficient subsampling for training complex language models

Efficient subsampling for training complex language models

引用

Conference on Empirical Methods in Natural language processing, EMNLP 2011

作者： Xu, Puyang Gunawardana, Asela Khudanpur, Sanjeev Department of Electrical and Computer Engineering Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States Microsoft Research Redmond WA 98052 United States

ISBN: (纸本)1937284115

We propose an efficient way to train maximum entropy language models (MELM) and neural network language models (NNLM). The advantage of the proposed method comes from a more robust and efficient subsampling technique. The original multi-class language modeling problem is transformed into a set of binary problems where each binary classifier predicts whether or not a particular word will occur. We show that the binarized model is as powerful as the standard model and allows us to aggressively subsample negative training examples without sacrificing predictive performance. Empirical results show that we can train MELM and NNLM at 1% ∼ 5% of the standard complexity with no loss in performance. © 2011 Association for Computational Linguistics.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Asymmetric acoustic model for accented speech recognition

Asymmetric acoustic model for accented speech recognition

引用

Asia-Pacific Signal and Information processing Association Annual Summit and Conference 2011, APSIPA ASC 2011

作者： Zhang, Chao Liu, Yi Zheng, Thomas Fang Tsinghua National Laboratory for Information Science and Technology Division of Technology Innovation and Development Center for Speech and Language Technologies Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

We propose to improve accented speech recognition performance by using asymmetric acoustic model. Our proposed model is generated based on reliable accent specific units and acoustic model reconstruction. The reliable units are extracted with time alignment recognition to cover accent variations at both acoustic and phonetic levels. The asymmetric acoustic model is obtained through selective decision tree merging together with dynamic Gaussian component selection in model reconstruction. The improved resolution of our proposed model is able to handle different levels of accented variations at different degrees. The effectiveness of our approach was evaluated on a typical Chinese accent. Our system outperforms traditional acoustic model reconstruction and MAP adaptation approaches by 8.28% and 7.14%, relatively on Syllable Error Rate (SER) reduction without sacrificing the performance on standard Mandarin speech.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

Radial Gaussianization with cluster-specific bias compensation

Radial Gaussianization with cluster-specific bias compensati...

引用

IEEE/SP Workshop on Statistical Signal processing (SSP)

作者： Shuai Huang Damianos Karakos Daguang Xu Center of Language and Speech Processing Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA Human Language Technology Center of Excellence Center of Language and Speech Processing Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA

In recent work, Lyu and Simoncelli [1] introduced radial Gaussianization (RG) as a very efficient procedure for transforming n-dimensional random vectors into Gaussian vectors with independent and identically distributed (i.i.d.) components. This entails transforming the norms of the data so that they become chi-distributed with n degrees of freedom. A necessary requirement is that the original data are generated by an isotropic distribution, that is, their probability density function (pdf) is constant over surfaces of n-dimensional spheres (or, more general, n-dimensional ellipsoids). The case of biases in the data, which is of great practical interest, is studied here; as we demonstrate with experiments, there are situations in which even very small amounts of bias can cause RG to fail. This becomes evident especially when the data form clusters in low-dimensional manifolds. To address this shortcoming, we propose a two-step approach which entails (i) first discovering clusters in the data and removing the bias from each, and (ii) performing RG on the bias-compensated data. In experiments with synthetic data, the proposed bias compensation procedure results in significantly better Gaus-sianization than the non-compensated RG method.

关键词： Principal component analysis Noise measurement Estimation Gaussian distribution Distributed databases Optimization Transforms

来源：评论

学校读者我要写书评

暂无评论

An in-car Chinese noise corpus for speech recognition

An in-car Chinese noise corpus for speech recognition

引用

2011 International Conference on Asian language processing, IALP 2011

作者： Hou, Jue Liu, Yi Zhang, Chao Huang, Shilei Center for Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Shenzhen Key Laboratory of Intelligent Media and Speech Shenzhen China

ISBN: (纸本)9780769545547

In this paper, we present an in-car Chinese noise corpus that can be used in simulating complicated car environment for robust speech recognition research and experiment. The corpus was collected in mainland China in 2009 and 2010. The corpus includes a diversity of car conditions including different car speed, open/close windows, weather conditions as well as environment conditions. Specially, the rumble strips are also taken into account due to the typical noise generated as the car is passing on. In order to use the corpus efficiently, we performed some acoustic signal analyses on those noise data, mainly focused on stationary properties and energy distribution in the frequency domain. We also performed ASR experiments using selected noise data from the corpus, by adding noise data to clean speech to simulate the in-car environment. The corpus is the first of its kind for in-car Chinese noise corpus, providing abundant and diversified samples for car noise speech recognition task. © 2011 IEEE.

关键词： speech recognition

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

Multistream robust speaker recognition based on speech intelligibility

Multistream robust speaker recognition based on speech intel...

引用

Annual Conference on Information sciences and Systems (CISS)

作者： Sridhar Krishna Nemala Mounya Elhilali Department of Electrical and Computer Engineering Center for Speech and Language Processing Johns Hopkins University Baltimore MD USA

Delimiting the most informative voice segments of an acoustic signal is often a crucial initial step for any speech processing system. In the current work, we propose a novel segmentation approach based on a perception-based measure of speech intelligibility. Unlike segmentation approaches based on various forms of voice-activity detection (VAD), the proposed segmentation approach exploits higher-level perceptual information about the signal intelligibility levels. This classification based on intelligibility estimates is integrated into a novel multistream framework for automatic speaker recognition task. The multistream system processes the input acoustic signal along multiple independent streams reflecting various levels of intelligibility and then fusing the decision scores from the multiple steams according to their intelligibility contribution. Our results show that the proposed multistream system achieves significant improvements both in clean and noisy conditions when compared with a baseline and a state-of-the-art voice-activity detection algorithm.

关键词： Computational modeling Robustness Noise

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44页 << < 28 29 30 31 32 33 34 35 36 37 > >>

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：