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

284 篇 会议
102 篇 期刊文献

馆藏范围

386 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

262 篇 工学
- 192 篇 计算机科学与技术...
- 176 篇 软件工程
- 66 篇 信息与通信工程
- 21 篇 机械工程
- 19 篇 生物工程
- 17 篇 控制科学与工程
- 14 篇 电气工程
- 14 篇 电子科学与技术（可...
- 10 篇 光学工程
- 9 篇 化学工程与技术
- 7 篇 生物医学工程（可授...
- 3 篇 仪器科学与技术
- 3 篇 动力工程及工程热...
- 2 篇 材料科学与工程（可...
- 2 篇 土木工程
163 篇 理学
- 109 篇 物理学
- 66 篇 数学
- 36 篇 统计学（可授理学、...
- 23 篇 生物学
- 20 篇 系统科学
- 10 篇 化学
- 1 篇 地球物理学
37 篇 管理学
- 27 篇 图书情报与档案管...
- 10 篇 管理科学与工程(可...
- 4 篇 工商管理
6 篇 法学
- 5 篇 社会学
- 1 篇 法学
2 篇 文学
- 2 篇 外国语言文学
- 1 篇 中国语言文学
1 篇 经济学
- 1 篇 应用经济学
1 篇 农学
1 篇 医学
1 篇 艺术学

主题

66 篇 speech recogniti...
41 篇 training
39 篇 hidden markov mo...
29 篇 neural machine t...
23 篇 machine translat...
20 篇 decoding
19 篇 handwriting reco...
18 篇 computer aided l...
16 篇 recurrent neural...
15 篇 feature extracti...
15 篇 transducers
14 篇 vocabulary
12 篇 databases
12 篇 error analysis
11 篇 speech
10 篇 pattern recognit...
10 篇 humans
9 篇 training data
9 篇 optimization
9 篇 context

机构

52 篇 human language t...
40 篇 human language t...
38 篇 apptek gmbh aach...
32 篇 human language t...
31 篇 human language t...
23 篇 apptek gmbh aach...
21 篇 human language t...
16 篇 human language t...
13 篇 human language t...
12 篇 pattern recognit...
10 篇 human language t...
9 篇 spoken language ...
9 篇 human language t...
8 篇 computer science...
8 篇 human language t...
6 篇 pattern recognit...
6 篇 human language t...
6 篇 human language t...
6 篇 human language t...
5 篇 a2ia sa

作者

213 篇 ney hermann
82 篇 hermann ney
61 篇 schlüter ralf
22 篇 ralf schluter
21 篇 ralf schlüter
20 篇 wuebker joern
18 篇 casacuberta fran...
18 篇 zeyer albert
18 篇 zhou wei
16 篇 gao yingbo
14 篇 kim yunsu
14 篇 herold christian
13 篇 mansour saab
13 篇 zeineldeen moham...
13 篇 patrick doetsch
13 篇 peitz stephan
13 篇 huck matthias
12 篇 peris álvaro
12 篇 peter jan-thorst...
12 篇 michel wilfried

语言

384 篇 英文
1 篇 西班牙文
1 篇 中文

检索条件"机构=Human Language Technology and Pattern"

共 386 条记录，以下是51-60 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：

Phrase Training Based Adaptation for Statistical Machine Translation 2

Phrase Training Based Adaptation for Statistical Machine Tra...

引用

2nd Workshop on Computational Linguistics for Literature, CLfL 2013 at the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: human language Technologies, NAACL-HLT 2013

作者： Mansour, Saab Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781937284473

We present a novel approach for translation model (TM) adaptation using phrase training. The proposed adaptation procedure is initialized with a standard general-domain TM, which is then used to perform phrase training on a smaller in-domain set. This way, we bias the probabilities of the general TM towards the in-domain distribution. Experimental results on two different lectures translation tasks show significant improvements of the adapted systems over the general ones. Additionally, we compare our results to mixture modeling, where we report gains when using the suggested phrase training adaptation method. © 2013 Association for Computational Linguistics

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

The Vicomtech-PRHLT Speech Transcription Systems for the IberSPEECH-RTVE 2018 Speech to Text Transcription Challenge 4

The Vicomtech-PRHLT Speech Transcription Systems for the Ibe...

引用

4th International Conference on Advances in Speech and language Technologies for Iberian languages, IberSPEECH 2018

作者： Arzelus, Haritz Álvarez, Aitor Bernath, Conrad García, Eneritz Granell, Emilio Martínez-Hinarejos, Carlos D. Vicomtech Human Speech and Language Technology Group Spain Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica de València Spain

This paper describes our joint submission to the IberSPEECH-RTVE Speech to Text Transcription Challenge 2018, which calls for automatic speech transcription systems to be evaluated in realistic TV shows. With the aim of building and evaluating systems, RTVE licensed around 569 hours of different TV programs, which were processed, re-aligned and revised in order to discard segments with imperfect transcriptions. This task reduced the corpus to 136 hours that we considered as nearly perfectly aligned audios and that we employed as in-domain data to train acoustic models. A total of 6 systems were built and presented to the evaluation challenge, three systems per condition. These recognition engines are different versions, evolution and configurations of two main architectures. The first architecture includes an hybrid LSTM-HMM acoustic model, where bidirectional LSTMs were trained to provide posterior probabilities for the HMM states. The language model corresponds to modified Kneser- Ney smoothed 3-gram and 9-gram models used for decoding and re-scoring of the lattices respectively. The second architecture includes an End-To-End based recognition system, which combines 2D convolutional neural networks as spectral feature extractor from spectrograms with bidirectional Gated Recurrent Units as RNN acoustic models. A modified Kneser-Ney smoothed 5-gram model was also integrated to re-score the E2E hypothesis. All the systems' outputs were then punctuated using bidirectional RNN models with attention mechanism and capitalized through recasing techniques. © 4th International Conference, IberSPEECH 2018.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Time conditioned search in automatic speech recognition reconsidered

Time conditioned search in automatic speech recognition reco...

引用

作者： Nolden, D. Ney, H. Schlüter, R. Human Language Technology and Pattern Recognition Group RWTH Aachen University Aachen Germany

In this paper we re-investigate the time conditioned search (TCS) method in comparison to the well known word conditioned search (WCS), and analyze its applicability on state-of-the-art large vocabulary continuous speech recognition tasks. In contrast to current standard approaches, time conditioned search offers theoretical advantages particularly in combination with huge vocabularies and huge language models, but it is difficult to combine with across word modelling, which was proven to be an important technique in automatic speech recognition. Our novel contributions for TCS are a pruning step during the recombination called Early Word End Pruning, an additional recombination technique called Context Recombination, the idea of a Startup Interval to reduce the number of started trees, and a mechanism to combine TCS with across word modelling. We show that, with these techniques, TCS can outperform WCS on current ASR tasks. © 2010 ISCA.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Exploring E2E speech recognition systems for new languages 4

Exploring E2E speech recognition systems for new languages

引用

4th International Conference on Advances in Speech and language Technologies for Iberian languages, IberSPEECH 2018

作者： Bernath, Conrad Álvarez, Aitor Arzelus, Haritz Martínez-Hinarejos, Carlos-D. Human Speech and Language Technology Group Vicomtech Spain Pattern Recognition and Human Language Technologies Research Center Universitat Politècnica de València Spain

Over the last few years, advances in both machine learning algorithms and computer hardware have led to significant improvements in speech recognition technology, mainly through the use of Deep Learning paradigms. As it was amply demonstrated in different studies, Deep Neural Networks (DNNs) have already outperformed traditional Gaussian Mixture Models (GMMs) at acoustic modeling in combination with Hidden Markov Models (HMMs). More recently, new attempts have focused on building end-to-end (E2E) speech recognition architectures, especially in languages with many resources like English and Chinese, with the aim of overcoming the performance of LSTM-HMM and more conventional systems. The aim of this work is first to present the different techniques that have been applied to enhance state-of-the-art E2E systems for American English using publicly available datasets. Secondly, we describe the construction of E2E systems for Spanish and Basque, and explain the strategies applied to overcome the problem of the limited availability of training data, especially for Basque as a low-resource language. At the evaluation phase, the three E2E systems are also compared with LSTM-HMM based recognition engines built and tested with the same datasets. © 4th International Conference, IberSPEECH 2018.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

TANDEM HMM WITH CONVOLUTIONAL NEURAL NETWORK FOR HANDWRITTEN WORD RECOGNITION

TANDEM HMM WITH CONVOLUTIONAL NEURAL NETWORK FOR HANDWRITTEN...

引用

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

作者： Bluche, Theodore Ney, Hermann Kermorvant, Christopher A2iA SA France LIMSI CNRS Spoken Language Processing Group France RWTH Aachen University Human Language Technology and Pattern Recognition Germany

ISBN: (纸本)9781479903566

In this paper, we investigate the combination of hidden Markov models and convolutional neural networks for handwritten word recognition. The convolutional neural networks have been successfully applied to various computer vision tasks, including handwritten character recognition. In this work, we show that they can replace Gaussian mixtures to compute emission probabilities in hidden Markov models (hybrid combination), or serve as feature extractor for a standard Gaussian HMM system (tandem combination). The proposed systems outperform a basic HMM based on either decorrelated pixels or handcrafted features. We validated the approach on two publicly available databases, and we report up to 60% (Rimes) and 35% (IAM) relative improvement compared to a Gaussian HMM based on pixel values. The final systems give comparable results to recurrent neural networks, which are the best systems since 2009.

关键词： Handwriting recognition Hidden Markov Model Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Hybrid language models for Open Vocabulary Continuous Speech Recognition using WFST

Hierarchical Hybrid Language models for Open Vocabulary Cont...

引用

2012 SAPA-SCALE Conference

作者： Shaik, M. Ali Basha Rybach, David Hahn, Stefan Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52056 Germany

One of the main challenges in automatic speech recognition is recognizing an open, partly unseen vocabulary. To implicitly reduce the out-of-vocabulary (OOV) rate, hybrid vocabularies consisting of full-words and sub-words are used. Nevertheless, when using sub-words, OOV rates are not necessarily zero. In this work, we propose the use of separate character level graphones (orthography and phoneme sequence pair) as sub-words to effectively obtain zero OOV rate. To minimize negative effects on the core vocabulary of the most frequent words, a hierarchical language modeling approach is proposed. We augment the first level hybrid language model with an OOV word class, which is replaced by character level graphone sequences using a second-level graphone based character language and acoustic model during search. This approach is realized on-the-fly using weighted finite state transducers. We recognize a significant fraction of OOVs on the Wall Street Journal corpus, compared to the full-word and former hybrid language model based approaches. © SAPA-SCALE 2012. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Morpheme based Factored language Models for German LVCSR

Morpheme based Factored Language Models for German LVCSR

引用

12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011

作者： El-Desoky Mousa, Amr Ali Basha Shaik, M. Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52056 Aachen Germany

German is a highly inflectional language, where a large number of words can be generated from the same root. It makes a liberal use of compounding leading to high Out-of-vocabulary (OOV) rates, and poor language Model (LM) probability estimates. Therefore, the use of morphemes for language modeling is considered a better choice for Large Vocabulary Continuous Speech Recognition (LVCSR) than the full-words. Thereby, better lexical coverage and less LM perplexities are achieved. On the other side, the use of Factored language Models (FLMs) is considered a successful approach that allows the integration of many information sources to get better LM probability estimates. In this paper, we try a combined methodology for language modeling where both morphological decomposition and factored language modeling are used in one model called morpheme based FLM. Finally, we obtain around 2.5% relative reduction in Word Error Rate (WER) with respect to a traditional full-words system. Copyright © 2011 ISCA.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Confidence-based discriminative training for model adaptation in offline Arabic handwriting recognition

Confidence-based discriminative training for model adaptatio...

引用

ICDAR2009 - 10th International Conference on Document Analysis and Recognition

作者： Dreuw, Philippe Heigold, Georg Ney, Hermann RWTH Aachen University Human Language Technology and Pattern Recognition Ahornstr 55 D-52056 Aachen Germany

ISBN: (纸本)9780769537252

We present a novel confidence-based discriminative training for model adaptation approach for an HMM based Arabic handwriting recognition system to handle different handwriting styles and their variations. Most current approaches are maximum-likelihood trained HMM systems and try to adapt their models to different writing styles using writer adaptive training, unsupervised clustering, or additional writer specific data. Discriminative training based on the Maximum Mutual Information criterion is used to train writer independent handwriting models. For model adaptation during decoding, an unsupervised confidence-based discriminative training on a word and frame level within a two-pass decoding process is proposed. Additionally, the training criterion is extended to incorporate a margin term. The proposed methods are evaluated on the IFN/ENIT Arabic handwriting database, where the proposed novel adaptation approach can decrease the word-error-rate by 33% relative. © 2009 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Using morpheme and syllable based sub-words for polish LVCSR

Using morpheme and syllable based sub-words for polish LVCSR

引用

36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

作者： Shaik, M. Ali Basha El-Desoky Mousa, Amr Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition - Computer Science Department RWTH Aachen University 52056 Aachen Germany

ISBN: (纸本)9781457705397

Polish is a synthetic language with a high morpheme-per-word ratio. It makes use of a high degree of inflection leading to high out-of-vocabulary (OOV) rates, and high language Model (LM) perplexities. This poses a challenge for Large Vocabulary and Continuous Speech Recognition (LVCSR) systems. Here, the use of morpheme and syllable based units is investigated for building sub-lexical LMs. A different type of sub-lexical units is proposed based on combining morphemic or syllabic units with corresponding pronunciations. Thereby, a set of grapheme-phoneme pairs called graphones are used for building LMs. A relative reduction of 3.5% in Word Error Rate (WER) is obtained with respect to a traditional system based on full-words. © 2011 IEEE.

关键词： Continuous speech recognition

来源：评论

学校读者我要写书评

暂无评论

Towards a Better Evaluation of Metrics for Machine Translation 5

Towards a Better Evaluation of Metrics for Machine Translati...

引用

5th Conference on Machine Translation, WMT 2020

作者： Stanchev, Peter Wang, Weiyue Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52056 Germany

ISBN: (纸本)9781948087810

An important aspect of machine translation is its evaluation, which can be achieved through the use of a variety of metrics. To compare these metrics, the workshop on statistical machine translation annually evaluates metrics based on their correlation with human judgement. Over the years, methods for measuring correlation with humans have changed, but little research has been performed on what the optimal methods for acquiring human scores are and how human correlation can be measured. In this work, the methods for evaluating metrics at both system- and segment-level are analyzed in detail and their shortcomings are pointed out. © 2020 Association for Computational Linguistics

关键词： Machine translation

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39页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：