检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Raissi, Tina Beck, Eugen Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University

Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their highly varying statistics require tying or smoothing to enable robust training. Usually, classification and regression trees are used for phonetic clustering, which is standard in hidden Markov model (HMM)-based systems. However, this solution introduces a secondary training objective and does not allow for end-to-end training. In this work, we address a direct phonetic context modeling for the hybrid deep neural network (DNN)/HMM, that does not build on any phone clustering algorithm for the determination of the HMM state inventory. By performing different decompositions of the joint probability of the center phoneme state and its left and right contexts, we obtain a factorized network consisting of different components, trained jointly. Moreover, the representation of the phonetic context for the network relies on phoneme embeddings. The recognition accuracy of our proposed models on the Switchboard task is comparable and outperforms slightly the hybrid model using the standard state-tying decision *** Codes 68T10 Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised training for large vocabulary translation using sparse lexicon and word classes

arXiv

引用

arXiv 2019年

作者： Kim, Yunsu Schamper, Julian Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University

We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text or seed lexicon. First, we solve the memory bottleneck and enforce the sparsity with a simple thresholding scheme for the lexicon. Second, we initialize the lexicon training with word classes, which efficiently boosts the performance. Our methods produced promising results on two large-scale unsupervised translation tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

ValenTo: Sentiment Analysis of Figurative language Tweets with Irony and Sarcasm 9

ValenTo: Sentiment Analysis of Figurative Language Tweets wi...

引用

9th International Workshop on Semantic Evaluation, SemEval 2015

作者： Farías, Delia Irazú Hernández Sulis, Emilio Patti, Viviana Ruffo, Giancarlo Bosco, Cristina Universitat Politècnica de València Pattern Recognition and Human Language Technology Spain University of Turin Dipartimento di Informatica Italy

ISBN: (纸本)9781941643402

This paper describes the system used by the ValenTo team in the Task 11, Sentiment Analysis of Figurative language in Twitter, at SemEval 2015. Our system used a regression model and additional external resources to assign polarity values. A distinctive feature of our approach is that we used not only word-sentiment lexicons providing polarity annotations, but also novel resources for dealing with emotions and psycholinguistic information. These are important aspects to tackle in figurative language such as irony and sarcasm, which were represented in the dataset. The system also exploited novel and standard structural features of tweets. Considering the different kinds of figurative language in the dataset our submission obtained good results in recognizing sentiment polarity in both ironic and sarcastic tweets. © 2015 Association for Computational Linguistics

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Performance Study of Cube Pruning for Large-Scale Hierarchical Machine Translation 7

A Performance Study of Cube Pruning for Large-Scale Hierarch...

引用

7th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2013

作者： Huck, Matthias Vilar, David Freitag, Markus Ney, Hermann Human Language Technology and Pattern Recognition Group Rwth Aachen University AachenD-52056 Germany Dfki GmbH Alt-Moabit 91c BerlinD-10559 Germany

ISBN: (纸本)9781937284473

In this paper, we empirically investigate the impact of critical configuration parameters in the popular cube pruning algorithm for decoding in hierarchical statistical machine translation. Specifically, we study how the choice of the k-best generation size affects translation quality and resource requirements in hierarchical search. We furthermore examine the influence of two different granularities of hypothesis recombination. Our experiments are conducted on the large-scale Chinese!English and Arabic!English NIST translation tasks. Besides standard hierarchical grammars, we also explore search with restricted recursion depth of hierarchical rules based on shallow-1 grammars. ©2013 Association for Computational Linguistics.

关键词： Computer aided language translation

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

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

ISBN: (纸本)9781424491407

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. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Speeding up 2D-warping for pose-invariant face recognition

Speeding up 2D-warping for pose-invariant face recognition

引用

International Conference on Automatic Face and Gesture recognition

作者： Harald Hanselmann Hermann Ney Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany

Recently, state-of-the-art recognition accuracies for pose-invariant face recognition have been achieved by using 2D-Warping methods in a nearest-neighbor framework. However, the main drawback of these methods is the high computational complexity. In this paper we address this issue. We use a simple and fast method to get a rough estimate of a 2D-Warping. This estimate can then be used to apply an image dependent warprange on the 2D-Warping algorithm, limit the possible poses or preselect the most likely classes. By this method we are able significantly reduce the runtime of a recently proposed 2D-Warping algorithm without sacrificing recognition accuracy.

关键词： Face recognition Accuracy Runtime Databases Complexity theory Manuals Face

来源：评论

学校读者我要写书评

暂无评论

The RWTH Large Vocabulary Arabic Handwriting recognition System

The RWTH Large Vocabulary Arabic Handwriting Recognition Sys...

引用

IAPR International Workshop on Document Analysis Systems, DAS

作者： Mahdi Hamdani Patrick Doetsch Michal Kozielski Amr El-Desoky Mousa Hermann Ney Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany

This paper describes the RWTH system for large vocabulary Arabic handwriting recognition. The recognizer is based on Hidden Markov Models (HMMs) with state of the art methods for visual/language modeling and decoding. The feature extraction is based on Recurrent Neural Networks (RNNs) which estimate the posterior distribution over the character labels for each observation. Discriminative training using the Minimum Phone Error (MPE) criterion is used to train the HMMs. The recognition is done with the help of n-gram language Models (LMs) trained using in-domain text data. Unsupervised writer adaptation is also performed using the Constrained Maximum Likelihood Linear Regression (CMLLR) feature adaptation. The RWTH Arabic handwriting recognition system gave competitive results in previous handwriting recognition competitions. The used techniques allows to improve the performance of the system participating in the OpenHaRT 2013 evaluation.

关键词： Hidden Markov models Handwriting recognition Feature extraction Training Vocabulary Speech recognition Context

来源：评论

学校读者我要写书评

暂无评论

Semantic cohesion model for phrase-based SMT

Semantic cohesion model for phrase-based SMT

引用

24th International Conference on Computational Linguistics, COLING 2012

作者： Feng, Minwei Sun, Weiwei Ney, Hermann Computer Science Department Human Language Technology and Pattern Recognition Group RWTH Aachen University Aachen Germany MOE Key Laboratory of Computational Linguistics Institute of Computer Science and Technology Peking University Beijing China

In this paper, we propose a novel semantic cohesion model. Our model utilizes the predicateargument structures as soft constraints and plays the role as a reordering model in the phrasebased statistical machine translation system. We build a translation system with GALE data. Experimental results on the NIST02, NIST03, NIST04, NIST05 and NIST08 Chinese-English tasks show that our model improves the baseline system by 0.93 BLEU 0.98 TER on average. We also compare our method with a syntax-augmented model (Cherry, 2008), and demonstrate the importance of predicate-argument semantics in machine translation. © 2012 The COLING.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

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

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

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：