检索结果-内蒙古大学图书馆

The rwth aachen german-english machine translation system for wmt 2015 10

The rwth aachen german-english machine translation system fo...

10th Workshop on Statistical Machine Translation, WMT 2015 at the 2015 Conference on Empirical Methods in Natural language Processing, EMNLP 2015

作者： Peter, Jan-Thorsten Toutounchi, Farzad Wuebker, Joern Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department Rwth Aachen University AachenD-52056 Germany

ISBN: (纸本)9781941643327

This paper describes the statistical machine translation system developed at RWTH Aachen University for the German!English translation task of the EMNLP 2015 Tenth Workshop on Statistical Machine Translation (WMT 2015). A phrase-based machine translation system was applied and augmented with hierarchical phrase reordering and word class language models. Further, we ran discriminative maximum expected BLEU training for our system. In addition, we utilized multiple feed-forward neural network language and translation models and a recurrent neural network language model for reranking. © EMNLP 2015. All rights reserved.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigations on sequence training of neural networks 40

Investigations on sequence training of neural networks

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Wiesler, Simon Golik, Pavel Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany LIMSI CNRS Spoken Language Processing Group Paris France

ISBN: (纸本)9781467369978

In this paper we present an investigation of sequence-discriminative training of deep neural networks for automatic speech recognition. We evaluate different sequence-discriminative training criteria (MMI and MPE) and optimization algorithms (including SGD and Rprop) using the RASR toolkit. Further, we compare the training of the whole network with that of the output layer only. Technical details necessary for a robust training are studied, since there is no consensus yet on the ultimate training recipe. The investigation extends our previous work on training linear bottleneck networks from scratch showing the consistently positive effect of sequence training. © 2015 IEEE.

关键词： deep neural networks optimization sequence training speech recognition

来源：评论

学校读者我要写书评

暂无评论

Improved strategies for a zero oov rate LVCSR system 40

Improved strategies for a zero oov rate LVCSR system

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Shaik, M. Ali Basha Mousa, Amr El-Desoky Hahn, Stefan Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition - Computer Science Department RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

ISBN: (纸本)9781467369978

In this work, multiple hierarchical language modeling strategies for a zero OOV rate large vocabulary continuous speech recognition system are investigated. In our previously proposed hierarchical approach, a full-word language model and a context independent character-level LM (CLM) are directly used during search. The novelty of this work is to jointly model the character-level prior and the pronunciation probabilities, to introduce across-word context into the characterlevel LM, and to properly normalize the character-level LM using prefix-tree based normalization for the hierarchical approach. Significant reductions in-terms of word error rates (WER) on the best full-word Quaero Polish LVCSR system are reported. © 2015 IEEE.

关键词： hierarchical LVCSR OOV prefix-tree

来源：评论

学校读者我要写书评

暂无评论

Sequence-discriminative training of recurrent neural networks 40

Sequence-discriminative training of recurrent neural network...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Voigtlaender, Paul Doetsch, Patrick Wiesler, Simon Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany LIMSI CNRS Spoken Language Processing Group Paris France

ISBN: (纸本)9781467369978

We investigate sequence-discriminative training of long shortterm memory recurrent neural networks using the maximum mutual information criterion. We show that although recurrent neural networks already make use of the whole observation sequence and are able to incorporate more contextual information than feed forward networks, their performance can be improved with sequence-discriminative training. Experiments are performed on two publicly available handwriting recognition tasks containing English and French handwriting. On the English corpus, we obtain a relative improvement in WER of over 11% with maximum mutual information (MMI) training compared to cross-entropy training. On the French corpus, we observed that it is necessary to interpolate the MMI objective function with cross-entropy. © 2015 IEEE.

关键词： handwriting recognition long shortterm memory recurrent neural networks sequence-discriminative training

来源：评论

学校读者我要写书评

暂无评论

Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables 40

Integrating Gaussian mixtures into deep neural networks: Sof...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Tuske, Zoltan Tahir, Muhammad Ali Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

ISBN: (纸本)9781467369978

In the hybrid approach, neural network output directly serves as hidden Markov model (HMM) state posterior probability estimates. In contrast to this, in the tandem approach neural network output is used as input features to improve classic Gaussian mixture model (GMM) based emission probability estimates. This paper shows that GMM can be easily integrated into the deep neural network framework. By exploiting its equivalence with the log-linear mixture model (LMM), GMM can be transformed to a large softmax layer followed by a summation pooling layer. Theoretical and experimental results indicate that the jointly trained and optimally chosen GMM and bottleneck tandem features cannot perform worse than a hybrid model. Thus, the question 'hybrid vs. tandem' simplifies to optimizing the output layer of a neural network. Speech recognition experiments are carried out on a broadcast news and conversations task using up to 12 feed-forward hidden layers with sigmoid and rectified linear unit activation functions. The evaluation of the LMM layer shows recognition gains over the classic softmax output. © 2015 IEEE.

关键词： ASR bottleneck DNN GMM hybrid LMM Log-linear mixture model neural network tandem

来源：评论

学校读者我要写书评

暂无评论

On the Benefits of Convolutional Neural Network Combinations in Offline Handwriting Recognition

On the Benefits of Convolutional Neural Network Combinations...

引用

International Workshop on Frontiers in Handwriting Recognition

作者： Dewi Suryani Patrick Doetsch Hermann Ney King Mongkut's University of Technology North Bangkok The Sirindhorn International Thai-German Graduate School of Engineering Bangkok Thailand Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781509009824

In this paper, we elaborate the advantages of combining two neural network methodologies, convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent neural networks, with the framework of hybrid hidden Markov models (HMM) for recognizing offline handwriting text. CNNs employ shift-invariant filters to generate discriminative features within neural networks. We show that CNNs are powerful tools to extract general purpose features that even work well for unknown classes. We evaluate our system on a Chinese handwritten text database and provide a GPU-based implementation that can be used to reproduce the experiments. All experiments were conducted with RWTH OCR, an open-source system developed at our institute.

关键词： Hidden Markov models Neurons Training Handwriting recognition Biological neural networks computer architecture Logic gates

来源：评论

学校读者我要写书评

暂无评论

Microblog Sentiment Analysis with Emoticon Space Model

引用

Journal of computer science & Technology 2015年第5期30卷 1120-1129页

作者：姜飞刘奕群栾焕博孙甲申朱璇张敏马少平 State Key Laboratory of Intelligent Technology and Systems Beijing 100084 China Tsinghua National Laboratory for Information Science and Technology Beijing 100084 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Language Computing Laboratory Samsung Research & Development Institute of China Beijing 100028 China

Emoticons have been widely employed to express different types of moods, emotions, and feelings in microblog environments. They are therefore regarded as one of the most important signals for microblog sentiment analysis. Most existing studies use several emoticons that convey clear emotional meanings as noisy sentiment labels or similar sentiment indicators. However, in practical microblog environments, tens or even hundreds of emoticons are frequently adopted and all emoticons have their own unique emotional meanings. Besides, a considerable number of emoticons do not have clear emotional meanings. An improved sentiment analysis model should not overlook these phenomena. Instead of manually assigning sentiment labels to several emoticons that convey relatively clear meanings, we propose the emoticon space model （ESM） that leverages more emotieons to construct word representations from a massive amount of unlabeled data. By projecting words and microblog posts into an emoticon space, the proposed model helps identify subjectivity, polarity, and emotion in microblog environments. The experimental results for a public microblog benchmark corpus （NLP＆CC 2013） indicate that ESM effectively leverages emoticon signals best runs. and outperforms previous state-of-the-art strategies and benchmark

关键词： microblog sentiment analysis emoticon space polarity classification subjectivity classification emotion clas-sification

来源：评论

学校读者我要写书评

暂无评论

DISCRIMINATIVELY TRAINED JOINT SPEAKER AND ENVIRONMENT REPRESENTATIONS FOR ADAPTATION OF DEEP NEURAL NETWORK ACOUSTIC MODELS

DISCRIMINATIVELY TRAINED JOINT SPEAKER AND ENVIRONMENT REPRE...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Maofan Yin Sunil Sivadas Kai Yu Bin Ma Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab. Department of Computer Science and Engineering Shanghai Jiao Tong University China Human Language Technology Lab. Institute for Infocomm Research Singapore

ISBN: (纸本)9781479999897

A recent trend in normalization of factors extraneous to a speech recognition task has been to explicitly introduce features related to the unwanted variability in the training of Deep Neural Networks (DNN). Typically, this is done by either perturbing the training set with models of these extraneous factors such as vocal tract length and environmental noise or augmenting the conventional spectral features with auxiliary information such as i-vector, noise spectrum, etc. Another emerging approach is to derive low dimensional representations of the factors from the hidden layers of DNN and use it for normalization of the acoustic model. Almost all of these approaches focus on either speaker or environment normalization. In this paper we propose a novel approach for estimating a compact joint representation of speakers and environment by training a DNN, with a bottleneck layer, to classify the i-vector features into speaker and environment labels by Multi-Task Learning (MTL). Another novelty is to learn this compact representation while learning to map the i-vector of a noisy utterance into its corresponding clean speaker ivector and noise-only i-vector. Experiments were conducted on an artificially noise-corrupted version of the WSJ corpus. The proposed compact joint speaker-environment representations show promising gains.

关键词： i-vector deep neural network speaker adaptation multi-task learning noise robustness Loudspeakers speaker adaptation Noise robustness Environments normalization Joints Neural network representations Speech recognition PARALLEL PROCESSING (computerS) Acoustic models Ambient Noise Vocal tract

来源：评论

学校读者我要写书评

暂无评论

Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions 40

Unsupervised adaptation of a denoising autoencoder by Bayesi...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Heymann, Jahn Haeb-Umbach, Reinhold Golik, Pavel Schluter, Ralf University of Paderborn Department of Communications Engineering Paderborn Germany RWTH Aachen University Human Language Technology and Pattern Recognition Computer Science Department Aachen Aachen Germany

ISBN: (纸本)9781467369978

The parametric Bayesian Feature Enhancement (BFE) and a datadriven Denoising Autoencoder (DA) both bring performance gains in severe single-channel speech recognition conditions. The first can be adjusted to different conditions by an appropriate parameter setting, while the latter needs to be trained on conditions similar to the ones expected at decoding time, making it vulnerable to a mismatch between training and test conditions. We use a DNN backend and study reverberant ASR under three types of mismatch conditions: different room reverberation times, different speaker to microphone distances and the difference between artificially reverberated data and the recordings in a reverberant environment. We show that for these mismatch conditions BFE can provide the targets for a DA. This unsupervised adaptation provides a performance gain over the direct use of BFE and even enables to compensate for the mismatch of real and simulated reverberant data. © 2015 IEEE.

关键词： deep neuronal networks denoising autoencoder feature enhancement robust speech recognition

来源：评论

学校读者我要写书评

暂无评论

HLTC-HKUST: A Neural Network Paraphrase Classifier using Translation Metrics, Semantic Roles and Lexical Similarity Features 9

HLTC-HKUST: A Neural Network Paraphrase Classifier using Tra...

引用

9th International Workshop on Semantic Evaluation, SemEval 2015

作者： Bertero, Dario Fung, Pascale Human Language Technology Center Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

ISBN: (纸本)9781941643402

This paper describes the system developed by our team (HLTC-HKUST) for task 1 of SemEval 2015 workshop about paraphrase classification and semantic similarity in Twitter. We trained a neural network classifier over a range of features that includes translation metrics, lexical and syntactic similarity score and semantic features based on semantic roles. The neural network was trained taking into consideration in the objective function the six different similarity levels provided in the corpus, in order to give as output a more fine-grained estimation of the similarity level of the two sentences, as required by subtask 2. With an F-score of 0.651 in the binary paraphrase classification subtask 1, and a Pearson coefficient of 0.697 for the sentence similarity subtask 2, we achieved respectively the 6th place and the 3rd place, above the average of what obtained by the other contestants. © 2015 Association for Computational Linguistics

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：