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261-270 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：

Hallucinating phrase translations for low resource MT 18

Hallucinating phrase translations for low resource MT

引用

18th Conference on Computational Natural language Learning, CoNLL 2014

作者： Irvine, Ann Callison-Burch, Chris Center for Language and Speech Processing Johns Hopkins University United States Computer and Information Science Dept. University of Pennsylvania United States

ISBN: (纸本)9781941643020

We demonstrate that "hallucinating" phrasal translations can significantly improve the quality of machine translation in low resource conditions. Our hallucinated phrase tables consist of entries composed from multiple unigram translations drawn from the baseline phrase table and from translations that are induced from monolingual corpora. The hallucinated phrase table is very noisy. Its translations are low precision but high recall. We counter this by introducing 30 new feature functions (including a variety of monolingually-estimated features) and by aggressively pruning the phrase table. Our analysis evaluates the intrinsic quality of our hallucinated phrase pairs as well as their impact in end-to-end Spanish-English and Hindi-English MT. © 2014 Association for Computational Linguistics.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

SemEval-2014 Task 4: Aspect Based Sentiment Analysis 8

SemEval-2014 Task 4: Aspect Based Sentiment Analysis

引用

8th International Workshop on Semantic Evaluation, SemEval 2014

作者： Pontiki, Maria D., Galanis J., Pavlopoulos H., Papageorgiou I., Androutsopoulos S., Manandhar Institute for Language and Speech Processing "Athena" Research Center Greece Dept. of Informatics Athens University of Economics and Business Greece Dept. of Computer Science University of York United Kingdom

ISBN: (纸本)9781941643242

Sentiment analysis is increasingly viewed as a vital task both from an academic and a commercial standpoint. The majority of current approaches, however, attempt to detect the overall polarity of a sentence, paragraph, or text span, irrespective of the entities mentioned (e.g., laptops) and their aspects (e.g., battery, screen). SemEval-2014 Task 4 aimed to foster research in the field of aspect-based sentiment analysis, where the goal is to identify the aspects of given target entities and the sentiment expressed for each aspect. The task provided datasets containing manually annotated reviews of restaurants and laptops, as well as a common evaluation procedure. It attracted 163 submissions from 32 teams. © 8th International Workshop on Semantic Evaluation, SemEval 2014 - co-located with the 25th International Conference on Computational Linguistics, COLING 2014, Proceedings. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

The Tutorbot corpus - A corpus for studying tutoring behaviour in multiparty face-to-face spoken dialogue 9

The Tutorbot corpus - A corpus for studying tutoring behavio...

引用

9th International Conference on language Resources and Evaluation, LREC 2014

作者： Koutsombogera, Maria Al Moubayed, Samer Bollepalli, Bajibabu Abdelaziz, Ahmed Hussen Johansson, Martin Lopes, José David Aguas Novikova, Jekaterina Oertel, Catharine Stefanov, Kalin Varol, Gül KTH Speech Music and Hearing Sweden Institute for Language and Speech Processing - Athena R.C. Greece Institute of Communication Acoustics Ruhr-Universität Bochum Germany Spoken Language Systems Laboratory INESC ID Portugal Department of Computer Science University of Bath United Kingdom Department of Computer Engineering Bogazici University Turkey

ISBN: (纸本)9782951740884

This paper describes a novel experimental setup exploiting state-of-the - art capture equipment to collect a multimodally rich game-solving collaborative multiparty dialogue corpus. The corpus is targeted and designed towards the development of a dialogue system platform to explore verbal and nonverbal tutoring strategies in multiparty spoken interactions. The dialogue task is centered on two participants involved in a dialogue aiming to solve a card-ordering game. The participants were paired into teams based on their degree of extraversion as resulted from a personality test. With the participants sits a tutor that helps them perform the task, organizes and balances their interaction and whose behavior was assessed by the participants after each interaction. Different multimodal signals captured and auto-synchronized by different audio-visual capture technologies, together with manual annotations of the tutor's behavior constitute the Tutorbot corpus. This corpus is exploited to build a situated model of the interaction based on the participants' temporally-changing state of attention, their conversational engagement and verbal dominance, and their correlation with the verbal and visual feedback and conversation regulatory actions generated by the tutor.

关键词： Visual communication

来源：评论

学校读者我要写书评

暂无评论

Tutoring robots multiparty multimodal social dialogue with an embodied tutor 9

Tutoring robots multiparty multimodal social dialogue with a...

引用

9th IFIPWG 5.5 International Summer Workshop on Multimodal Interfaces, eNTERFACE 2013

作者： Moubayed, Samer Al Beskow, Jonas Bollepalli, Bajibabu Hussen-Abdelaziz, Ahmed Johansson, Martin Koutsombogera, Maria Lopes, José David Novikova, Jekaterina Oertel, Catharine Skantze, Gabriel Stefanov, Kalin Varol, Gül KTH Speech Music and Hearing Sweden Institute for Language and Speech Processing AthenaRC Greece Spoken Language Systems Laboratory INESC ID Lisboa Portugal Department of Computer Science University of Bath United Kingdom Institute of Communication Acoustics Ruhr-Universität Bochum Germany Department of Computer Engineering Bo ğaziçi University Turkey

ISBN: (纸本)9783642551420

This project explores a novel experimental setup towards building spoken, multi-modally rich, and human-like multiparty tutoring agent. A setup is developed and a corpus is collected that targets the development of a dialogue system platform to explore verbal and nonverbal tutoring strategies in multiparty spoken interactions with embodied agents. The dialogue task is centered on two participants involved in a dialogue aiming to solve a card-ordering game. With the participants sits a tutor that helps the participants perform the task and organizes and balances their interaction. Different multimodal signals captured and auto-synchronized by different audio-visual capture technologies were coupled with manual annotations to build a situated model of the interaction based on the participants personalities, their temporally-changing state of attention, their conversational engagement and verbal dominance, and the way these are correlated with the verbal and visual feedback, turn-management, and conversation regulatory actions generated by the tutor. At the end of this chapter we discuss the potential areas of research and developments this work opens and some of the challenges that lie in the road ahead. © IFIP International Federation for Information processing 2014

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Elastic and Efficient Virtual Network Provisioning for Cloud-Based Multi-tier Applications

Elastic and Efficient Virtual Network Provisioning for Cloud...

引用

International Conference on Parallel processing (ICPP)

作者： Meng Shen Ke Xu Fan Li Kun Yang Liehuang Zhu Lei Guan Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology P. R. China Department of Computer Science Tsinghua University P. R. China School of Computer Science & Electronic Engineering University of Essex UK The ISN National Key Lab XiDian University P. R. China School of Management & Economics Beijing Institute of Technology P. R. China

ISBN: (纸本)9781467375887

The multi-tier architecture is prevalently adopted by cloud applications, such as the three-tier web application. It is highly desirable for both tenants and providers to provide virtual networks in an efficient and elastic way, where tenant applications can automatically scale in or out with varying workloads and providers can accommodate as many requests as possible in the underlying network. However, due to potential conflicts between efficiency and elasticity, it is challenging to achieve these two goals simultaneously in abstracting tenant requirements and designing corresponding provisioning algorithms. In this paper, we propose an efficient and elastic virtual network provisioning solution called Easy Alloc, which is comprised of an elasticity-aware abstraction model and a virtual network provisioning algorithm. To accurately capture the tenant requirement and maintain the provisioning simplicity for providers, the elasticity-aware model enables two types of decoupling, i.e., Always-on VMs for normal load and on-demand VMs for dynamic scaling, and the bandwidth requirement of each VM for intra- and inter-tier communications. Then we formulate the virtual network provisioning as an overhead minimization problem, where the objective simultaneously considers the bandwidth and elasticity overhead. Due to the NP-completeness of this problem, we leverage two heuristics, slot reservation and tier iteration, to obtain an efficient algorithm. Extensive simulation results show that compared with a typical elasticity-agnostic method under a heavy load, Easy Alloc enables a 9% increase of request acceptance rate and a 16.8% improvement of the successful extension rate. To the best of our knowledge, this is the first work targeting at the elastic virtual network provisioning.

关键词： Bandwidth Elasticity Cloud computing Algorithm design and analysis Load modeling Resource management

来源：评论

学校读者我要写书评

暂无评论

Discriminative confidence measure using linear combination of duration-based features and acoustic-based scores in keyword spotting

Discriminative confidence measure using linear combination o...

引用

International Symposium on Telecommunications, IST

作者： Mohammad Mohsen Goodarzi Yasser Shekofteh Iman Sarraf Rezaei Jahanshah Kabudian Speech and Natural Language Processing Group Research Center of Intelligent Signal Processing (RCISP) Tehran Iran Department of Computer Engineering and Information Technology Razi University Kermanshah Iran

One of the most important steps in a keyword spotting (KWS) system is a post-processing procedure to compute a confidence measure (CM) for each hypothesized keyword. The CM is commonly estimated by likelihood-based acoustic scores. However durations of the detected keyword, which include useful information, has not been studied directly in the KWS systems. In this paper, three duration-based features are proposed for such system. Also, using linear discriminant analysis (LDA), the proposed duration-based features are discriminatively combined with the acoustic scores and used as the final discriminative CM (DCM) in the KWS system. The proposed DCM results up to 11.3% improvement in FOM against to the conventional likelihood-based CM over a Persian conversational telephone speech database.

关键词： speech speech recognition Hidden Markov models Acoustics Acoustic measurements Databases Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Speaker adaptation of hybrid NN/HMM model for speech recognition based on singular value decomposition

Speaker adaptation of hybrid NN/HMM model for speech recogni...

引用

International Symposium on Chinese Spoken language processing

作者： Shaofei Xue Hui Jiang Lirong Dai National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China Hefei Department of Electrical Engineering and Computer Science York University Toronto Canada

Recently several speaker adaptation methods have been proposed for deep neural network (DNN) in many large vocabulary continuous speech recognition (LVCSR) tasks. However, only a few methods rely on tuning the weight matrices in trained DNNs to optimize system performance since it is very prone to over-fitting especially when some class labels are missing in the adaptation data. In this paper, we propose a new speaker adaptation method for the hybrid NN/HMM speech recognition model based on singular value decomposition (SVD). We apply SVD on the weight matrices in trained DNNs, and then tune diagonal matrices with the adaptation data. This solves the over-fitting problem since we can change the weight matrices slightly by only modifying the singular values. We evaluate the proposed adaptation method in two standard speech recognition tasks, namely TIMIT phone recognition and large vocabulary speech recognition in the Switchboard task. Experimental results have shown that it is effective to adapt large DNN models using only a small amount of adaptation data. For example, the Switchboard results have shown that the proposed SVD-based adaptation method may achieve up to 3-6% relative error reduction using only a few dozens of adaptation utterances per speaker.

关键词： Hidden Markov models Adaptation models speech recognition Neural networks speech Matrix decomposition Signal processing

来源：评论

学校读者我要写书评

暂无评论

DIRECT ADAPTATION OF HYBRID DNN/HMM MODEL FOR FAST SPEAKER ADAPTATION IN LVCSR BASED ON SPEAKER CODE

DIRECT ADAPTATION OF HYBRID DNN/HMM MODEL FOR FAST SPEAKER A...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： Shaofei Xue Ossama Abdel-Hamid Hui Jiang Lirong Dai National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China Hefei P. R. China Department of Electrical Engineering and Computer Science York University Toronto Canada

ISBN: (纸本)9781479928941

Recently an effective fast speaker adaptation method using discriminative speaker code (SC) has been proposed for the hybrid DNN-HMM models in speech recognition [1]. This adaptation method depends on a joint learning of a large generic adaptation neural network for all speakers as well as multiple small speaker codes using the standard back-propagation algorithm. In this paper, we propose an alternative direct adaptation in model space, where speaker codes are directly connected to the original DNN models through a set of new connection weights, which can be estimated very efficiently from all or part of training data. As a result, the proposed method is more suitable for large scale speech recognition tasks since it eliminates the time-consuming training process to estimate another adaptation neural networks. In this work, we have evaluated the proposed direct SC-based adaptation method in the large scale 320-hr Switchboard task. Experimental results have shown that the proposed SC-based rapid adaptation method is very effective not only for small recognition tasks but also for very large scale tasks. For example, it has shown that the proposed method leads to up to 8% relative reduction in word error rate in Switchboard by using only a very small number of adaptation utterances per speaker (from 10 to a few dozens). Moreover, the extra training time required for adaptation is also significantly reduced from the method in [1].

关键词： Loudspeakers speech recognition Error analysis HYBRID

来源：评论

学校读者我要写书评

暂无评论

SEQUENCE TRAINING OF MULTIPLE DEEP NEURAL NETWORKS FOR BETTER PERFORMANCE AND FASTER TRAINING SPEED

SEQUENCE TRAINING OF MULTIPLE DEEP NEURAL NETWORKS FOR BETTE...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： Pan Zhou Lirong Dai Hui Jiang National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China Hefei P. R. China Department of Electrical Engineering and Computer Science York University Toronto Canada

ISBN: (纸本)9781479928941

Recently, sequence level discriminative training methods have been proposed to fine-tune deep neural networks (DNN) after the frame-level cross entropy (CE) training to further improve recognition performance of DNNs. In our previous work, we have proposed a new cluster-based multiple DNNs structure and its parallel training algorithm based on the frame-level cross entropy criterion, which can significantly expedite CE training with multiple GPUs. In this paper, we extend to full sequence training for the multiple DNNs structure for better performance and meanwhile we also consider a partial parallel implementation of sequence training using multiple GPUs for faster training speed. In this work, it is shown that sequence training can be easily extended to multiple DNNs by slightly modifying error signals in output layer. Many implementation steps in sequence training of multiple DNNs can still be parallelized across multiple GPUs for better efficiency. Experiments on the Switchboard task have shown that both frame-level CE training and sequence training of multiple DNNs can lead to massive training speedup with little degradation in recognition performance. Comparing with the state-of-the-art DNN, 4-cluster multiple DNNs model with similar size can achieve more than 7 times faster in CE training and about 1.5 times faster in sequence training when using 4 GPUs.

关键词： Functional training Training Fasting speed cerium Neural network Cross Entropy

来源：评论

学校读者我要写书评

暂无评论

IMPROVING DEEP NEURAL NETWORKS FOR LVCSR USING DROPOUT AND SHRINKING STRUCTURE

IMPROVING DEEP NEURAL NETWORKS FOR LVCSR USING DROPOUT AND S...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： Shiliang Zhang Yebo Bao Pan Zhou Hui Jiang Lirong Dai National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei Anhui P. R. China Department of Electrical Engineering and Computer Science York University Toronto Canada

ISBN: (纸本)9781479928941

Recently, the hybrid deep neural networks and hidden Markov models (DNN/HMMs) have achieved dramatic gains over the conventional GMM/HMMs method on various large vocabulary continuous speech recognition (LVCSR) tasks. In this paper, we propose two new methods to further improve the hybrid DNN/HMMs model: i) use dropout as pre-conditioner (DAP) to initialize DNN prior to back-propagation (BP) for better recognition accuracy;ii) employ a shrinking DNN structure (sDNN) with hidden layers decreasing in size from bottom to top for the purpose of reducing model size and expediting computation time. The proposed DAP method is evaluated in a 70-hour Mandarin transcription (PSC) task and the 309-hour Switchboard (SWB) task. Compared with the traditional greedy layer-wise pre-trained DNN, it can achieve about 10% and 6.8% relative recognition error reduction for PSC and SWB tasks respectively. In addition, we also evaluate sDNN as well as its combination with DAP on the SWB task. Experimental results show that these methods can reduce model size to 45% of original size and accelerate training and test time by 55%, without losing recognition accuracy.

关键词： Hidden Markov models Training Neural networks speech recognition speech Computational modeling Switches

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 << < 23 24 25 26 27 28 29 30 31 32 > >>

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：