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71-80 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：

Enhancing and Adversarial: Improve ASR with Speaker Labels 48

Enhancing and Adversarial: Improve ASR with Speaker Labels

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhou, Wei Wu, Haotian Xu, Jingjing Zeineldeen, Mohammad Luscher, Christoph Schluter, Ralf Ney, Hermann Rwth Aachen University Human Language Technology and Pattern Recognition Computer Science Department Aachen52074 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9781728163277

ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In this work, we study how to best apply these two opposite objectives with speaker labels to improve conformer-based ASR. We also propose a novel adaptive gradient reversal layer for stable and effective adversarial training without tuning effort. Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training. We also explore their combination for further improvement, achieving the same performance as i-vectors plus adversarial training. Our best speaker-based MTL achieves 7% relative improvement on the Switchboard Hub5'00 set. We also investigate the effect of such speaker-based MTL w.r.t. cleaner dataset and weaker ASR NN. © 2023 IEEE.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers 48

Lattice-Free Sequence Discriminative Training for Phoneme-Ba...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Zijian Zhou, Wei Schluter, Ralf Ney, Hermann Rwth Aachen University Human Language Technology and Pattern Recognition Computer Science Department Aachen52074 Germany AppTek GmbH Aachen52062 Germany

ISBN: (纸本)9781728163277

Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models, are rarely investigated in RNN-Transducers. In this work, we propose three lattice-free training objectives, namely lattice-free maximum mutual information, lattice-free segment-level minimum Bayes risk, and lattice-free minimum Bayes risk, which are used for the final posterior output of the phoneme-based neural transducer with a limited context dependency. Compared to criteria using N-best lists, lattice-free methods eliminate the decoding step for hypotheses generation during training, which leads to more efficient training. Experimental results show that lattice-free methods gain up to 6.5% relative improvement in word error rate compared to a sequence-level cross-entropy trained model. Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance. © 2023 IEEE.

关键词： neural transducer sequence discriminative training Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Training of Neural Transducer for Speech recognition 23

Efficient Training of Neural Transducer for Speech Recogniti...

引用

23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022

作者： Zhou, Wei Michel, Wilfried Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52074 Aachen Germany AppTek GmbH 52062 Aachen Germany

As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated neural network models of growing size and increasing training epochs. While strong computation resources seem to be the prerequisite of training superior models, we try to overcome it by carefully designing a more efficient training pipeline. In this work, we propose an efficient 3-stage progressive training pipeline to build highly-performing neural transducer models from scratch with very limited computation resources in a reasonable short time period. The effectiveness of each stage is experimentally verified on both Librispeech and Switchboard corpora. The proposed pipeline is able to train transducer models approaching state-of-the-art performance with a single GPU in just 2-3 weeks. Our best conformer transducer achieves 4.1% WER on Librispeech test-other with only 35 epochs of training. Copyright © 2022 ISCA.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Improved training of end-to-end attention models for speech recognition 19

Improved training of end-to-end attention models for speech ...

引用

19th Annual Conference of the International Speech Communication, INTERSPEECH 2018

作者： Zeyer, Albert Irie, Kazuki Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52062 Germany AppTek United States NNAISENSE Switzerland

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we report the state-of-the-art word error rates (WER) of 3.54% on the dev-clean and 3.82% on the test-clean evaluation subsets of LibriSpeech. We introduce a new pretraining scheme by starting with a high time reduction factor and lowering it during training, which is crucial both for convergence and final performance. In some experiments, we also use an auxiliary CTC loss function to help the convergence. In addition, we train long short-term memory (LSTM) language models on subword units. By shallow fusion, we report up to 27% relative improvements in WER over the attention baseline without a language model. © 2018 International Speech Communication Association. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Are very large N-best lists useful for SMT?

Are very large N-best lists useful for SMT?

引用

2007 human language technology Conference of the North American Chapter of the Association of Computational Linguistics, NAACL-HLT 2007

作者： Hasan, Saša Zens, Richard Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University AachenD-52056 Germany

This paper describes an efficient method to extract large n-best lists from a word graph produced by a statistical machine translation system. The extraction is based on the k shortest paths algorithm which is efficient even for very large k. We show that, although we can generate large amounts of distinct translation hypotheses, these numerous candidates are not able to significantly improve overall system performance. We conclude that large n-best lists would benefit from better discriminating models. © 2007 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

Efficient phrase-table representation for machine translation with applications to online MT and speech translation

Efficient phrase-table representation for machine translatio...

引用

human language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007

作者： Zens, Richard Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 - Computer Science Department RWTH Aachen University D-52056 Aachen Germany

In phrase-based statistical machine translation, the phrase-table requires a large amount of memory. We will present an efficient representation with two key properties: on-demand loading and a prefix tree structure for the source phrases. We will show that this representation scales well to large data tasks and that we are able to store hundreds of millions of phrase pairs in the phrase-table. For the large Chinese-English NIST task, the memory requirements of the phrase-table are reduced to less than 20MB using the new representation with no loss in translation quality and speed. Additionally, the new representation is not limited to a specific test set, which is important for online or real-time machine translation. One problem in speech translation is the matching of phrases in the input word graph and the phrase-table. We will describe a novel algorithm that effectively solves this combinatorial problem exploiting the prefix tree data structure of the phrase-table. This algorithm enables the use of significantly larger input word graphs in a more efficient way resulting in improved translation quality. © 2007 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

The RWTH Machine Translation System for IWSLT 2008 5

The RWTH Machine Translation System for IWSLT 2008

引用

5th International Workshop on Spoken language Translation, IWSLT 2008

作者： Vilar, David Stein, Daniel Zhang, Yuqi Matusov, Evgeny Mauser, Arne Bender, Oliver Mansour, Saab Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University AachenD-52056 Germany

RWTH's system for the 2008 IWSLT evaluation consists of a combination of different phrase-based and hierarchical statistical machine translation systems. We participated in the translation tasks for the Chinese-to-English and Arabic-to-English language pairs. We investigated different preprocessing techniques, reordering methods for the phrase-based system, including reordering of speech lattices, and syntax-based enhancements for the hierarchical systems. We also tried the combination of the Arabic-to-English and Chinese-to-English outputs as an additional submission. © 2008 International Workshop on Spoken language Translation, IWSLT 2008. All rights reserved.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Are unaligned words important for machine translation?

Are unaligned words important for machine translation?

引用

13th Annual Conference of the European Association for Machine Translation, EAMT 2009

作者： Zhang, Yuqi Matusov, Evgeny Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 - Computer Science Department RWTH Aachen University D-52056 Aachen Germany

In this paper, we deal with the problem of a large number of unaligned words in automatically learned word alignments for machine translation (MT). These unaligned words are the reason for ambiguous phrase pairs extracted by a statistical phrase-based MT system. In translation, this phrase ambiguity causes deletion and insertion errors. We present hard and optional deletion approaches to remove the unaligned words in the source language sentences. Improvements in translation quality are achieved both on large and small vocabulary tasks with the presented methods. © 2009 European Association for Machine Translation.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

The RWTH Statistical Machine Translation System for the IWSLT 2006 Evaluation 3

The RWTH Statistical Machine Translation System for the IWSL...

引用

3rd International Workshop on Spoken language Translation, IWSLT 2006

作者： Mauser, Arne Zens, Richard Matusov, Evgeny Hasan, Saša Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University AachenD-52056 Germany

We give an overview of the RWTH phrase-based statistical machine translation system that was used in the evaluation campaign of the International Workshop on Spoken language Translation (IWSLT) 2006. The system was ranked first with respect to the BLEU measure in all language pairs it was used Using a two-pass aproach, we first generate the N best translation candidates. The second pass consists of rescoring and reranking these candidates. We will give a description of the search algorithm as well as of the models used in each pass. We will also describe our method for dealing with punctuation restoration, in order to overcome the difficulties of spoken language translation. This work also includes a brief description of the system combination done by the partners participating in the European TC-Star project. © 2006 International Workshop on Spoken language Translation, IWSLT 2006. All rights reserved.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

The RWTH Machine Translation System for IWSLT 2007 4

The RWTH Machine Translation System for IWSLT 2007

引用

4th International Workshop on Spoken language Translation, IWSLT 2007

作者： Mauser, Arne Vilar, David Leusch, Gregor Zhang, Yuqi Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University AachenD-52056 Germany

The RWTH system for the IWSLT 2007 evaluation is a combination of several statistical machine translation systems. The combination includes Phrase-Based models, a n-gram translation model and a hierarchical phrase model. We describe the individual systems and the method that was used for combining the system outputs. Compared to our 2006 system, we newly introduce a hierarchical phrase-based translation model and show improvements in system combination for Machine Translation. RWTH participated in the Italian-to-English and Chinese-to-English translation directions. © 2007 International Workshop on Spoken language Translation, IWSLT 2007. All rights reserved.

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22页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：