检索结果-内蒙古大学图书馆

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

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

Powerful extensions to CRFS for grapheme to phoneme conversion

Powerful extensions to CRFS for grapheme to phoneme conversi...

引用

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

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

A comparative analysis of dynamic network decoding

A comparative analysis of dynamic network decoding

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

ISBN: (纸本)9781457705380

The use of statically compiled search networks for ASR systems using huge vocabularies and complex language models often becomes challenging in terms of memory requirements. Dynamic network decoders introduce additional computations in favor of significantly lower memory consumption. In this paper we investigate the properties of two well-known search strategies for dynamic network decoding, namely history conditioned tree search and WFST-based search using dynamic transducer composition. We analyze the impact of the differences in search graph representation, search space structure, and language model look-ahead techniques. Experiments on an LVCSR task illustrate the influence of the compared properties.

关键词： Decoding Transducers Hidden Markov models History Speech recognition Context Vocabulary

来源：评论

学校读者我要写书评

暂无评论

RASR/NN: THE RWTH NEURAL NETWORK TOOLKIT FOR SPEECH recognition

RASR/NN: THE RWTH NEURAL NETWORK TOOLKIT FOR SPEECH RECOGNIT...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

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

ISBN: (纸本)9781479928941

This paper describes the new release of RASR - the open source version of the well-proven speech recognition toolkit developed and used at RWTH Aachen University. The focus is put on the implementation of the NN module for training neural network acoustic models. We describe code design, configuration, and features of the NN module. The key feature is a high flexibility regarding the network topology, choice of activation functions, training criteria, and optimization algorithm, as well as a built-in support for efficient GPU computing. The evaluation of run-time performance and recognition accuracy is performed exemplary with a deep neural network as acoustic model in a hybrid NN/HMM system. The results show that RASR achieves a state-of-the-art performance on a real-world large vocabulary task, while offering a complete pipeline for building and applying large scale speech recognition systems.

关键词： Speech recognition Acoustic models Neural network runtime performance Optimization algorithms speech recognition system Buildings

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

A comparative study on vocabulary reduction for phrase table smoothing

arXiv

引用

arXiv 2019年

作者： Kim, Yunsu Guta, Andreas Wuebker, Joern Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Aachen Germany Lilt Inc

This work systematically analyzes the smoothing effect of vocabulary reduction for phrase translation models. We extensively compare various word-level vocabularies to show that the performance of smoothing is not significantly affected by the choice of vocabulary. This result provides empirical evidence that the standard phrase translation model is extremely sparse. Our experiments also reveal that vocabulary reduction is more effective for smoothing large-scale phrase tables. Copyright © 2019, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison and combination of different CRBE based MLP features for LVCSR

Comparison and combination of different CRBE based MLP featu...

引用

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

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

Multi Layer Perceptron (MLP) features extracted from different types of critical band energies (CRBE) - derived from MFCC, GT, and PLP pipeline - are compared on French broadcast news and conversational speech recognition task. Though the MLP structure is kept fixed, ROVER combination of different CRBE based systems leads to 4% relative improvement. Furthermore, aiming at the combination of state-of-the-art features based on various signal analysis methods into one single stream, posterior feature space based combination technique is proposed. The speaker normalized features originated from different CRBEs are merged after additional MLP training by Dempster-Shafer rule. The performance of these posterior features unifying the different CRBE based features is superior to the best single CRBE based posterior features by 6% relative. Further results reveal that the concatenated cepstral and unified posterior features perform nearly as well as the ROVER combination of the different CRBE based systems.

关键词： Feature extraction Mel frequency cepstral coefficient Speech Training Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

The Varied Impacts of Energy Storage and Photovoltaics on Fossil Fuel Emissions

The Varied Impacts of Energy Storage and Photovoltaics on Fo...

引用

IEEE Power and Energy Society General Meeting

作者： Emily Barrett Brandon Thayer Karen Studarus Seemita Pal Pattern Recognition and Human Language Technology Research Center Universitat Politecnica de Valencia Valencia Spain

ISBN: (纸本)9781538622131;9781538622124

The emissions consequences of smart grid technologies can be significant but are not always intuitive. This is particularly true in the implementation of energy storage (ES) to enable the installation of solar photovoltaic (PV) systems. Using the web-based calculator at and prototypical distribution feeders, this paper explores the CO_2, SO_2 and NO_x impacts of ES deployed with solar PV, where the energy storage system is operated to minimize load variation assuming hourly dispatch. Five regions of the country were explored using 15 prototypical distribution feeders and 2015 historical data. Impacts vary in direction, magnitude, and trend, and require a context-dependent screening method for faithful representation.

关键词： Meteorology Load modeling Fossil fuels Energy storage Smart grids Data models Photovoltaic systems

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：