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

146 篇 会议
68 篇 期刊文献

馆藏范围

214 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

151 篇 工学
- 111 篇 计算机科学与技术...
- 98 篇 软件工程
- 44 篇 信息与通信工程
- 13 篇 控制科学与工程
- 12 篇 电气工程
- 11 篇 电子科学与技术（可...
- 8 篇 机械工程
- 6 篇 生物工程
- 5 篇 化学工程与技术
- 5 篇 生物医学工程（可授...
- 4 篇 光学工程
- 2 篇 动力工程及工程热...
101 篇 理学
- 75 篇 物理学
- 38 篇 数学
- 19 篇 统计学（可授理学、...
- 12 篇 系统科学
- 7 篇 生物学
- 5 篇 化学
- 1 篇 地球物理学
17 篇 管理学
- 11 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
- 3 篇 工商管理
- 2 篇 公共管理
4 篇 医学
- 4 篇 临床医学
- 2 篇 基础医学(可授医学...
- 2 篇 公共卫生与预防医...
3 篇 法学
- 2 篇 社会学
- 1 篇 法学
1 篇 经济学
- 1 篇 应用经济学
1 篇 教育学
- 1 篇 体育学
1 篇 农学

主题

51 篇 speech recogniti...
15 篇 hidden markov mo...
15 篇 training
13 篇 neural machine t...
12 篇 machine translat...
12 篇 transducers
11 篇 computer aided l...
11 篇 decoding
9 篇 recurrent neural...
8 篇 speech
8 篇 feature extracti...
8 篇 neural network
8 篇 error analysis
7 篇 modelling langua...
6 篇 vocabulary
6 篇 optimization
6 篇 handwriting reco...
6 篇 humans
6 篇 automatic speech...
5 篇 hierarchical sys...

机构

40 篇 human language t...
37 篇 apptek gmbh aach...
32 篇 human language t...
20 篇 human language t...
10 篇 human language t...
9 篇 human language t...
8 篇 computer science...
8 篇 human language t...
7 篇 spoken language ...
7 篇 apptek gmbh aach...
6 篇 human language t...
6 篇 human language t...
6 篇 human language t...
5 篇 human language t...
4 篇 human language t...
3 篇 human language t...
3 篇 rwth aachen univ...
3 篇 limsi cnrs spoke...
3 篇 human language t...
2 篇 computer vision ...

作者

141 篇 ney hermann
55 篇 schlüter ralf
36 篇 hermann ney
16 篇 zeyer albert
16 篇 zhou wei
14 篇 gao yingbo
14 篇 ralf schluter
12 篇 ralf schlüter
12 篇 mansour saab
12 篇 zeineldeen moham...
12 篇 michel wilfried
12 篇 zens richard
11 篇 herold christian
10 篇 bahar parnia
10 篇 peitz stephan
9 篇 peter jan-thorst...
9 篇 schluter ralf
9 篇 freitag markus
9 篇 wang weiyue
8 篇 wuebker joern

语言

214 篇 英文

检索条件"机构=Human Language Technology and Pattern Recognition Group Computer Science"

共 214 条记录，以下是121-130 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：

A CRITICAL EVALUATION OF STOCHASTIC ALGORITHMS FOR CONVEX OPTIMIZATION

A CRITICAL EVALUATION OF STOCHASTIC ALGORITHMS FOR CONVEX OP...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Simon Wiesler Alexander Richard Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781479903573

Log-linear models find a wide range of applications in pattern recognition. The training of log-linear models is a convex optimization problem. In this work, we compare the performance of stochastic and batch optimization algorithms. Stochastic algorithms are fast on large data sets but can not be parallelized well. In our experiments on a broadcast conversations recognition task, stochastic methods yield competitive results after only a short training period, but when spending enough computational resources for parallelization, batch algorithms are competitive with stochastic algorithms. We obtained slight improvements by using a stochastic second order algorithm. Our best log-linear model outperforms the maximum likelihood trained Gaussian mixture model baseline although being ten times smaller.

关键词： discriminative models optimization speech recognition

来源：评论

学校读者我要写书评

暂无评论

Investigations on the use of morpheme level features in language Models for Arabic LVCSR

Investigations on the use of morpheme level features in Lang...

引用

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

作者： Amr El-Desoky Mousa Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition-Computer Science Department RWTH Aachen University Aachen Germany

A major challenge for Arabic Large Vocabulary Continuous Speech recognition (LVCSR) is the rich morphology of Arabic, which leads to high Out-of-vocabulary (OOV) rates, and poor language Model (LM) probabilities. In such cases, the use of morphemes rather than full-words is considered a better choice for LMs. Thereby, higher lexical coverage and less LM perplexities are achieved. On the other side, an effective way to increase the robustness of LMs is to incorporate features of words into LMs. In this paper, we investigate the use of features derived for morphemes rather than words. Thus, we combine the benefits of both morpheme level and feature rich modeling. We compare the performance of stream-based, class-based and Factored LMs (FLMs) estimated over sequences of morphemes and their features for performing Arabic LVCSR. A relative reduction of 3.9% in Word Error Rate (WER) is achieved compared to a word-based system.

关键词： Computational modeling Mathematical model Lattices humans Speech recognition USA Councils Interpolation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical hybrid MLP/HMM or rather MLP features for a discriminatively trained Gaussian HMM: A comparison for offline handwriting recognition

Hierarchical hybrid MLP/HMM or rather MLP features for a dis...

引用

IEEE International Conference on Image Processing

作者： Philippe Dreuw Patrick Doetsch Christian Plahl Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

We use neural network based features extracted by a hierarchical multilayer-perceptron (MLP) network either in a hybrid MLP/HMM approach or to discriminatively retrain a Gaussian hidden Markov model (GHMM) system in a tandem approach. MLP networks have been successfully used to model long-term and non-linear features dependencies in automatic speech and optical character recognition. In offline hand writing recognition, MLPs have been mostly used for isolated character and word recognition in hybrid approaches. Here we analyze MLPs within an LVCSR framework for continuous handwriting recognition using discriminative MMI/MPE training. Especially hybrid MLP/HMM and discriminatively retrained MLP-GHMM tandem approaches are evaluated. Significant improvements and competitive results are re ported for a closed-vocabulary task on the IfN/ENIT Arabic handwriting database and for a large-vocabulary task using the IAM English handwriting database.

关键词： Hidden Markov models Handwriting recognition Training Databases Feature extraction Text recognition Character recognition

来源：评论

学校读者我要写书评

暂无评论

EM-style optimization of hidden conditional random fields for grapheme-to-phoneme conversion

EM-style optimization of hidden conditional random fields fo...

引用

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

作者： Georg Heigold Stefan Hahn Patrick Lehnen Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

We have recently proposed an EM-style algorithm to optimize log-linear models with hidden variables. In this paper, we use this algorithm to optimize a hidden conditional random field, i.e., a conditional random field with hidden variables. Similar to hidden Markov models, the alignments are the hidden variables in the examples considered. Here, EM-style algorithms are iterative optimization algorithms which are guaranteed to improve the training criterion in each iteration without the need for tuning step sizes, sophisticated update schemes or numerical line optimization (with hardly predictable complexity). This is a rather strong property which conventional gradient-based optimization algorithms do not have. We present experimental results for a grapheme-to-phoneme conversion task and compare the convergence behavior of the EM-style algorithm with L-BFGS and Rprop.

关键词： Optimization Training Geographic Information Systems Mathematical model Convergence Error analysis Equations

来源：评论

学校读者我要写书评

暂无评论

DISCRIMINATIVE HMMS, LOG-LINEAR MODELS, AND CRFS: WHAT IS THE DIFFERENCE?

DISCRIMINATIVE HMMS, LOG-LINEAR MODELS, AND CRFS: WHAT IS TH...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： G. Heigold S. Wiesler M. Nussbaum-Thom P. Lehnen R. Schluter H. Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781424442959

Recently, there have been many papers studying discriminative acoustic modeling techniques like conditional random fields or discriminative training of conventional Gaussian HMMs. This paper will give an overview of the recent work and progress. We will strictly distinguish between the type of acoustic models on the one hand and the training criterion on the other hand. We will address two issues in more detail: the relation between conventional Gaussian HMMs and conditional random fields and the advantages of formulating the training criterion as a convex optimization problem. Experimental results for various speech tasks will be presented to carefully evaluate the different concepts and approaches, including both a digit string and large vocabulary continuous speech recognition tasks.

关键词： speech recognition hidden Markov model discriminative training log-linear model conditional random field

来源：评论

学校读者我要写书评

暂无评论

Faster sequence training

Faster sequence training

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Albert Zeyer Ilia Kulikov Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52062 Germany

ISBN: (纸本)9781509041183

It has been shown that sequence-discriminative training can improve the performance for large vocabulary continuous speech recognition. Our main contribution is a novel method for reducing the computation time of any sort of sequence training while only slightly decreasing the overall performance. The method allows to parallelize the forward propagation through the network, the loss and loss gradient calculation which will provide a frame-wise error signal, and an independent forward and back propagation using that error signal. That last step can be calculated in a frame-wise manner and thus allows to use frame chunking to further improve the runtime. The loss calculation can itself be parallelized over many sequences. In addition to several experiments which outline the runtime gains, we also provide a convergence proof sketch. We extend on the research of sequence training of bidirectional long-short term memory ((B)LSTM) networks and provide an overview and comparison over different criteria. We have published all the code as part of our RETURNN and RASR framework including our training setup configurations.

关键词： sequence training LSTM computation time parallelization computational time parallelization Functional training Runtime forward propagation Training Fasting

来源：评论

学校读者我要写书评

暂无评论

Returnn: The RWTH extensible training framework for universal recurrent neural networks

Returnn: The RWTH extensible training framework for universa...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Patrick Doetsch Albert Zeyer Paul Voigtlaender Ilia Kulikov Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52062 Germany

ISBN: (纸本)9781509041183

In this work we release our extensible and easily configurable neural network training software. It provides a rich set of functional layers with a particular focus on efficient training of recurrent neural network topologies on multiple GPUs. The source of the software package is public and freely available for academic research purposes and can be used as a framework or as a standalone tool which supports a flexible configuration. The software allows to train state-of-the-art deep bidirectional long short-term memory (LSTM) models on both one dimensional data like speech or two dimensional data like handwritten text and was used to develop successful submission systems in several evaluation campaigns.

关键词： recurrent neural networks lstm rnn speech recognition software package multi-gpu recurrent neural nets Software packages Speech recognition EXPANDABLE research purposes Frameworks Functional training

来源：评论

学校读者我要写书评

暂无评论

Phase difference of filter-stable part-tones as acoustic feature

Phase difference of filter-stable part-tones as acoustic fea...

引用

IEEE/SP Workshop on Statistical Signal Processing (SSP)

作者： Zoltán Tüske Friedhelm R. Drepper Ralf Schlüter Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

A part-tone decomposition of voiced sections of speech is introduced, which is adapted with high accuracy to the frequency of the glottal oscillator of the speaker. The iterative replacement of the center filter frequency contours (chosen locally as linear chirp) of the non-stationary bandpass filters converges extremely fast and leads to the extraction of filter-stable part-tones with uncorrupted phases. In contrast to phases of frequency decomposition with a priori defined, constant filter frequencies, the phase differences of filter-stable part-tones promise to become a useful supplement of the amplitude based acoustic features used for conventional automatic speech recognition. The derived phase features are tested in vowel classification experiments based on the phonetically rich TIMIT database.

关键词： Speech Harmonic analysis Equations Time frequency analysis Mel frequency cepstral coefficient Speech processing

来源：评论

学校读者我要写书评

暂无评论

Silence is golden: Modeling non-speech events in WFST-based dynamic network decoders

Silence is golden: Modeling non-speech events in WFST-based ...

引用

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

作者： David Rybach Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

Models for silence are a fundamental part of continuous speech recognition systems. Depending on application requirements, audio data segmentation, and availability of detailed training data annotations, it may be necessary or beneficial to differentiate between other non-speech events, for example breath and background noise. The integration of multiple non-speech models in a WFST-based dynamic network decoder is not straightforward, because these models do not perfectly fit in the transducer framework. This paper describes several options for the transducer construction with multiple non-speech models, shows their considerable different characteristics in memory and runtime efficiency, and analyzes the impact on the recognition performance.

关键词： Hidden Markov models Transducers Decoding Context Speech Noise Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition

A comprehensive study of deep bidirectional LSTM RNNS for ac...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Albert Zeyer Patrick Doetsch Paul Voigtlaender Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52062 Germany

ISBN: (纸本)9781509041183

Recent experiments show that deep bidirectional long short-term memory (BLSTM) recurrent neural network acoustic models outperform feedforward neural networks for automatic speech recognition (ASR). However, their training requires a lot of tuning and experience. In this work, we provide a comprehensive overview over various BLSTM training aspects and their interplay within ASR, which has been missing so far in the literature. We investigate on different variants of optimization methods, batching, truncated backpropagation, and regularization techniques such as dropout, and we study the effect of size and depth, training models of up to 10 layers. This includes a comparison of computation times vs. recognition performance. Furthermore, we introduce a pretraining scheme for LSTMs with layer-wise construction of the network showing good improvements especially for deep networks. The experimental analysis mainly was performed on the Quaero task, with additional results on Switchboard. The best BLSTM model gave a relative improvement in word error rate of over 15% compared to our best feed-forward baseline on our Quaero 50h task. All experiments were done using RETURNN and RASR, RWTH's extensible training framework for universal recurrent neural networks and ASR toolkit. The training configuration files are publicly available.

关键词： acoustic modeling LSTM RNN acoustic modeling Speech recognition recurrent neural nets aquifer storage and recovery Functional training feedforward neural nets Bidirectional

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22页 << < 9 10 11 12 13 14 15 16 17 18 > >>

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：