检索结果-内蒙古大学图书馆

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

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

ISBN: (纸本)9781457705380

Conditional Random Fields (CRFs) have proven to per form well on natural language processing tasks like name transliteration, concept tagging or grapheme-to-phoneme (g2p) conversion. The aim of this paper is to propose some extension to the state-of-the-art CRF systems for these tasks. Since the number of features can grow rapidly, a method for features selection is very helpful to boost performance. A combination of L1 and L2 regularization (elastic net) has been adopted and implemented within the Rprop optimization algorithm. Usually, dependencies on the target side are limited to bigram dependencies since the computational complexity grows exponentially with the history length. We present a modified CRF decoding where a conventional language model on target side is integrated into the CRF search process. Thus, larger contexts can be taken into account. Besides these two main parts, the already published margin-extension to the CRF training criterion has been adopted.

关键词： Training Context Context modeling Optimization Natural language processing Software algorithms 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

Feature selection for log-linear acoustic models

Feature selection for log-linear acoustic models

引用

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

作者： S. Wiesler A. Richard Y. Kubo R. Schlüter H. Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

ISBN: (纸本)9781457705380

Log-linear acoustic models have been shown to be competitive with Gaussian mixture models in speech recognition. Their high training time can be reduced by feature selection. We compare a simple univariate feature selection algorithm with ReliefF - an efficient multivariate algorithm. An alternative to feature selection is ℓ 1 -regularized training, which leads to sparse models. We observe that this gives no speedup when sparse features are used, hence feature selection methods are preferable. For dense features, ℓ 1 -regularization can reduce training and recognition time. We generalize the well known Rprop algorithm for the optimization of ℓ 1 -regularized functions. Experiments on the Wall Street Journal corpus showed that a large number of sparse features could be discarded without loss of performance. A strong regularization led to slight performance degradations, but can be useful on large tasks, where training the full model is not tractable.

关键词： Training Hidden Markov models Acoustics Speech recognition Polynomials Optimization Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Incorporating alignments into Conditional Random Fields for grapheme to phoneme conversion

Incorporating alignments into Conditional Random Fields for ...

引用

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

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

Conditional Random Fields (CRFs) are a state-of-the-art approach to natural language processing tasks like grapheme-to phoneme (g2p) conversion which is used to produce pronunciations or pronunciation variants for almost all ASR pronunciation lexica. One drawback of CRFs is that for training, an alignment is needed between graphemes and phonemes, usually even 1-to-l. The quality of the g2p result heavily depends on this alignment. Since these alignments are usually not annotated within the corpora, external models have to be used to produce such an alignment in a preprocessing step. In this work, we propose two approaches to integrate the alignment generation directly and efficiently into the CRF training process. Whereas the first approach relies on linear segmentation as starting point, the second approach considers all possible alignments given certain constraints. Both methods have been evaluated on two English g2p tasks, namely NETtalk and Celex, on which state-of-the-art results have been reported in the literature. The proposed approaches lead to results comparable to the state-of-the art.

关键词： Training Joints Hidden Markov models Biological system modeling Manuals Automata Mathematical model

来源：评论

学校读者我要写书评

暂无评论

An open science resource for establishing reliability and reproducibility in functional connectomics

引用

Scientific data 2014年第1期1卷 140049页

作者： Xi-Nian Zuo Jeffrey S Anderson Pierre Bellec Rasmus M Birn Bharat B Biswal Janusch Blautzik John C S Breitner Randy L Buckner Vince D Calhoun F Xavier Castellanos Antao Chen Bing Chen Jiangtao Chen Xu Chen Stanley J Colcombe William Courtney R Cameron Craddock Adriana Di Martino Hao-Ming Dong Xiaolan Fu Qiyong Gong Krzysztof J Gorgolewski Ying Han Ye He Yong He Erica Ho Avram Holmes Xiao-Hui Hou Jeremy Huckins Tianzi Jiang Yi Jiang William Kelley Clare Kelly Margaret King Stephen M LaConte Janet E Lainhart Xu Lei Hui-Jie Li Kaiming Li Kuncheng Li Qixiang Lin Dongqiang Liu Jia Liu Xun Liu Yijun Liu Guangming Lu Jie Lu Beatriz Luna Jing Luo Daniel Lurie Ying Mao Daniel S Margulies Andrew R Mayer Thomas Meindl Mary E Meyerand Weizhi Nan Jared A Nielsen David O'Connor David Paulsen Vivek Prabhakaran Zhigang Qi Jiang Qiu Chunhong Shao Zarrar Shehzad Weijun Tang Arno Villringer Huiling Wang Kai Wang Dongtao Wei Gao-Xia Wei Xu-Chu Weng Xuehai Wu Ting Xu Ning Yang Zhi Yang Yu-Feng Zang Lei Zhang Qinglin Zhang Zhe Zhang Zhiqiang Zhang Ke Zhao Zonglei Zhen Yuan Zhou Xing-Ting Zhu Michael P Milham Key Laboratory of Behavioral Science and Magnetic Resonance Imaging Research Center Institute of Psychology Chinese Academy of Sciences Chaoyang Beijing 100101 China Faculty of Psychology Southwest University Beibei Chongqing 400715 China. Division of Neuroradiology University of Utah Salt Lake City Utah 84132 USA. Unité de neuroimagerie fonctionnelle Centre de recherche de l'institut universitaire de gériatrie de Montréal Université de Montréal Montreal Quebec Canada H3W 1W5. Department of Psychiatry University of Wisconsin-Madison Madison Wisconsin 53719 USA. Department of Biomedical Engineering New Jersey Institute of Technology Newark New Jersey 07102 USA. Institute of Clinical Radiology Ludwig-Maximilians-University 80336 Munich Germany. Centre for Studies on Prevention of Alzheimer's Disease Department of Psychiatry Douglas Institute McGill University Faculty of Medicine Montreal Quebec Canada H4H 1R3. Department of Psychology Harvard University Cambridge Massachussetts 02138 USA. Mind Research Network Albuquerque New Mexico 87106 USA. Nathan S. Kline Institute for Psychiatric Research Orangeburg New York 10962 USA Phyllis Green and Randolph Cōwen Institute for Pediatric Neuroscience the Child Study Center at NYU Langone Medical Center New York New York 10016 USA. Center for Cognition and Brain Disorders Hangzhou Normal University Gongshu Hangzhou Zhejiang 311121 China. Nathan S. Kline Institute for Psychiatric Research Orangeburg New York 10962 USA. Center for the Developing Brain Child Mind Institute New York New York 10022 USA. University of Chinese Academy of Sciences Shijingshan Beijing 100049 China. State Key Laboratory of Brain and Cognitive Science Institute of Psychology Chinese Academy of Sciences Chaoyang Beijing 100101 China. Huaxi MR Research Center (HMRRC) Department of Radiology West China Hospital of Sichuan University Wuhou Chengdu Sichuan 610041 China. Max Planck Research Group for Neuroanatomy & C

Efforts to identify meaningful functional imaging-based biomarkers are limited by the ability to reliably characterize inter-individual differences in human brain function. Although a growing number of connectomics-based measures are reported to have moderate to high test-retest reliability, the variability in data acquisition, experimental designs, and analytic methods precludes the ability to generalize results. The Consortium for Reliability and Reproducibility (CoRR) is working to address this challenge and establish test-retest reliability as a minimum standard for methods development in functional connectomics. Specifically, CoRR has aggregated 1,629 typical individuals' resting state fMRI (rfMRI) data (5,093 rfMRI scans) from 18 international sites, and is openly sharing them via the International Data-sharing Neuroimaging Initiative (INDI). To allow researchers to generate various estimates of reliability and reproducibility, a variety of data acquisition procedures and experimental designs are included. Similarly, to enable users to assess the impact of commonly encountered artifacts (for example, motion) on characterizations of inter-individual variation, datasets of varying quality are included.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-stationary feature extraction for automatic speech recognition

Non-stationary feature extraction for automatic speech recog...

引用

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

作者： Zoltán Tüske Pavel Golik Ralf Schlüter Friedhelm R. Drepper Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Zentralinstitut für Elektronik Forschungszentrum Jülich (KFA) Julich Germany

In current speech recognition systems mainly Short-Time Fourier Transform based features like MFCC are applied. Dropping the short-time stationarity assumption of the voiced speech, this paper introduces the non-stationary signal analysis into the ASR framework. We present new acoustic features extracted by a pitch-adaptive Gammatone filter bank. The noise robustness was proved on AURORA 2 and 4 tasks, where the proposed features outperform the standard MFCC. Furthermore, successful combination experiments via ROVER indicate the differences between the new features and MFCC.

关键词： Mel frequency cepstral coefficient Harmonic analysis Feature extraction Speech Speech recognition Time frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Warp that smile on your face: Optimal and smooth deformations for face recognition

Warp that smile on your face: Optimal and smooth deformation...

引用

International Conference on Automatic Face and Gesture recognition

作者： Tobias Gass Leonid Pishchulin Philippe Dreuw Hermann Ney Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany Computer Vision Laboratory ETH Zurich Switzerland Computer Vision and Multimodal Computing MPI Informatics Saarbruecken Germany

In this work, we present novel warping algorithms for full 2D pixel-grid deformations for face recognition. Due to high variation in face appearance, face recognition is considered a very difficult task, especially if only a single reference image, for example a mug-shot, per face is available. Usually model-based approaches with additional training data are used to cope with several types of variation occurring in facial imaging. Image warping contrarily yields a distance measure which is invariant with regard to several types of variation. This allows for precise recognition even using only very few reference observations. Due to the computationally complex problem of optimal 2D warping, pseudo-2D warping-based approaches in the past represented strong approximations of the original problem, and were mainly successful on data with low variability or rectified images. We propose a novel 2D warping method which is globally optimal and makes no prior assumtions on the data variability besides two-dimensional smootheness constraints which both avoid local mirroring and gaps and significantly speed up the optimization. Furthermore, we show that occlusion handling is imperative to obtain smooth warpings in a variety of domains. We evaluate our novel algorithm on various well known databases, such as the AR-Face and CMU-PIE database, and provide a detailed comparison to existing warping approaches. We show that by using simple relative 2D constraints, strong local features and a kernel, which is robust w.r.t. occlusions, our computationally complex approaches outperform state-of-the-art results for recognizing faces under varying expressions, occlusions and poses. Most interestingly, we achieve higher accuracy using fewer training instances per class compared to methods learning a model of the 3D shape.

关键词： Pixel Face Face recognition Optimization Databases Approximation methods Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Constrained energy minimization for matching-based image recognition

Constrained energy minimization for matching-based image rec...

引用

2010 20th International Conference on pattern recognition, ICPR 2010

作者： Gass, Tobias Dreuw, Phillippe Ney, Hermann RWTH Aachen University Human Language Technology and Pattern Recognition Germany

ISBN: (纸本)9780769541099

We propose to use energy minimization in MRFs for matching-based image recognition tasks. To this end, the Tree-Reweighted Message Passing algorithm is modified by geometric constraints and efficiently used by exploiting the guaranteed monotonicity of the lower bound within a nearest-neighbor based classification framework. The constraints allow for a speedup linear to the dimensionality of the reference image, and the lower bound allows to optimally prune the nearest-neighbor search without loosing accuracy, effectively allowing to increase the number of optimization iterations without an effect on runtime. We evaluate our approach on well-known OCR and face recognition tasks and on the latter outperform current state-of-the-art. © 2010 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Sign language Machine Translation Overkill 7

Sign Language Machine Translation Overkill

引用

7th International Workshop on Spoken language Translation, IWSLT 2010

作者： Stein, Daniel Schmidt, Christoph Ney, Hermann Human Language Technology and Pattern Recognition RWTH Aachen University Germany

Sign languages represent an interesting niche for statistical machine translation that is typically hampered by the scarceness of suitable data, and most papers in this area apply only a few, well-known techniques and do not adapt them to small-sized corpora. In this paper, we will propose new methods for common approaches like scaling factor optimization and alignment merging strategies which helped improve our baseline. We also conduct experiments with different decoders and employ state-of-the-art techniques like soft syntactic labels as well as trigger-based and discriminative word lexica and system combination. All methods are evaluated on one of the largest sign language corpora available. © IWSLT 2010. 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

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：