检索结果-内蒙古大学图书馆

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

作者： Robin Schmitt Albert Zeyer Mohammad Zeineldeen Ralf Schlűter Hermann Ney Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany AppTek GmbH Aachen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We sometimes observe monotonically decreasing cross-attention weights in our Conformer-based global attention-based encoder-decoder (AED) models, negatively affecting performance compared to monotonically increasing attention weights. Further investigation shows that the Conformer encoder reverses the sequence in the time dimension. We analyze the initial behavior of the decoder cross-attention mechanism and find that it encourages the Conformer encoder self-attention to build a connection between the initial frames and all other informative frames. Furthermore, we show that, at some point in training, the self-attention module of the Conformer starts dominating the output over the preceding feed-forward module, which then only allows the reversed information to pass through. We propose methods and ideas of how this flipping can be avoided and investigate a novel method to obtain label-frame-position alignments by using the gradients of the label log probabilities w.r.t. the encoder input frames.

关键词： Training Signal processing Acoustics Decoding Speech processing

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Transformer-Based Models to Different Linguistic Perturbations: A Case of Study in Irony Detection

引用

Expert Systems 2025年第6期42卷

作者： Ortega-Bueno, Reynier Fersini, Elisabetta Rosso, Paolo Pattern Recognition and Human Language Technology Center Universitat Politècnica de València Cami de Vera S/N Valencia Spain Department of Informatics Systems and Communication Università degli Studi di Milano-Bicocca Viale Sarca 336 Milan Italy ValgrAI–Valencian Graduate School and Research Network of Artificial Intelligence Valencia Valencia Spain

This study investigates the robustness of Transformer models in irony detection addressing various textual perturbations, revealing potential biases in training data concerning ironic and non-ironic classes. The perturbations involve three distinct approaches, each progressively increasing in complexity. The first approach is word masking, which employs wild-card characters or utilises BERT-specific masking through the mask token provided by BERT models. The second approach is word substitution, replacing the bias word with a contextually appropriate alternative. Lastly, paraphrasing generates a new phrase while preserving the original semantic meaning. We leverage Large language Models (GPT 3.5 Turbo) and human inspection to ensure linguistic correctness and contextual coherence for word substitutions and paraphrasing. The results indicate that models are susceptible to these perturbations, and paraphrasing and word substitution demonstrate the most significant impact on model predictions. The irony class appears to be particularly challenging for models when subjected to these perturbations. The SHAP and LIME methods are used to correlate variations in attribution scores with prediction errors. A notable difference in the Total Variation of attribution scores is observed between original examples and cases involving bias word substitution or masking. Among the corpora used, TwSemEval2018 emerges as the most challenging. Regarding model performance, Transformer-based models such as RoBERTa and BERTweet demonstrate superior overall performance addressing these perturbations. This research contributes to understanding the robustness and limitations of irony detection models, highlighting areas for improvement in model design and training data curation. © 2025 John Wiley & Sons Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Extensions of the Sign language recognition and Translation Corpus RWTH-PHOENIX-Weather 9

Extensions of the Sign Language Recognition and Translation ...

引用

9th International Conference on language Resources and Evaluation (LREC)

作者： Forster, Jens Schmidt, Christoph Koller, Oscar Bellgardt, Martin Ney, Hermann Human Language Technology and Pattern Recognition RWTH Aachen University Germany

ISBN: (纸本)9782951740884

This paper introduces the RWTH-PHOENIX-Weather 2014, a video-based, large vocabulary, German sign language corpus which has been extended over the last two years, tripling the size of the original corpus. The corpus contains weather forecasts simultaneously interpreted into sign language which were recorded from German public TV and manually annotated using glosses on the sentence level and semi-automatically transcribed spoken German extracted from the videos using the open-source speech recognition system RASR. Spatial annotations of the signers' hands as well as shape and orientation annotations of the dominant hand have been added for more than 40k respectively 10k video frames creating one of the largest corpora allowing for quantitative evaluation of object tracking algorithms. Further, over 2k signs have been annotated using the SignWriting annotation system, focusing on the shape, orientation, movement as well as spatial contacts of both hands. Finally, extended recognition and translation setups are defined, and baseline results are presented.

关键词： Sign language Corpus Automatic recognition and Translation

来源：评论

学校读者我要写书评

暂无评论

Tailored design of Audio–Visual Speech recognition models using Branchformers

引用

Computer Speech & language 2025年 94卷

作者： David Gimeno-Gómez Carlos D. Martínez-Hinarejos Pattern Recognition and Human Language Technology (PRHLT) research center Universitat Politècnica de València Camino de Vera s/n Valencia 46022 Spain

Recent advances in Audio–Visual Speech recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed through the design of models composed of two independent encoders, each dedicated to a specific modality. However, while recent works have explored unified audio–visual encoders, determining the optimal cross-modal architecture remains an ongoing challenge. Furthermore, such approaches often rely on models comprising vast amounts of parameters and high computational cost training processes. In this paper, we aim to bridge this research gap by introducing a novel audio–visual framework. Our proposed method constitutes, to the best of our knowledge, the first attempt to harness the flexibility and interpretability offered by encoder architectures, such as the Branchformer, in the design of parameter-efficient AVSR systems. To be more precise, the proposed framework consists of two steps: first, estimating audio- and video-only systems, and then designing a tailored audio–visual unified encoder based on the layer-level branch scores provided by the modality-specific models. Extensive experiments on English and Spanish AVSR benchmarks covering multiple data conditions and scenarios demonstrated the effectiveness of our proposed method. Even when trained on a moderate scale of data, our models achieve competitive word error rates (WER) of approximately 2.5% for English and surpass existing approaches for Spanish, establishing a new benchmark with an average WER of around 9.1%. These results reflect how our tailored AVSR system is able to reach state-of-the-art recognition rates while significantly reducing the model complexity w.r.t. the prevalent approach in the field. Code and pre-trained models are available at https://***/david-gimeno/tailored-avsr .

关键词： Audio–visual speech recognition Branchformer Architecture design Unified audio–visual encoder Interpretability Parameter efficiency

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

White-space models for offline Arabic handwriting recognition

White-space models for offline Arabic handwriting recognitio...

引用

作者： Dreuw, Philippe Jonas, Stephan Ney, Hermann Human Language Technology and Pattern Recognition RWTH Aachen University Germany

ISBN: (纸本)9781424421756

We propose to explicitly model white-spaces for Arabic handwriting recognition within different writing variants. Position-dependent character shapes in Arabic handwriting allow for large white-spaces between characters even within words. Here, a separate character model for white-spaces in combination with a lexicon using different writing variants and character model length adaptation is proposed. Current handwriting recognition systems model the white-spaces implicitly within the character models leading to possibly degraded models, or try to explicitly segment the Arabic words into pieces of Arabic words being prone to segmentation errors. Several white-space modeling approaches are analyzed on the well known IFN/ENIT database and outperform the best reported error rates. © 2008 IEEE.

关键词： Character recognition

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

A Deep Learning Approach to Machine Transliteration 4

A Deep Learning Approach to Machine Transliteration

引用

4th Workshop on Statistical Machine Translation, WMT 2009, immediately preceding the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009

作者： Deselaers, Thomas Hasan, Sǎsa Bender, Oliver Ney, Hermann Human Language Technology And Pattern Recognition Group RWTH Aachen University Germany

In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show that deep belief networks have certain properties which are very interesting for transliteration and possibly also for translation and that a combination with conventional techniques leads to an improvement over both components on an Arabic-English transliteration task. ©2009 Association for Computational Linguistics.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SURF-face: Face recognition under viewpoint consistency constraints

SURF-face: Face recognition under viewpoint consistency cons...

引用

2009 20th British Machine Vision Conference, BMVC 2009

作者： Dreuw, Philippe Steingrube, Pascal Hanselmann, Harald Ney, Hermann Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany

ISBN: (纸本)1901725391

We analyze the usage of Speeded Up Robust Features (SURF) as local descriptors for face recognition. The effect of different feature extraction and viewpoint consistency constrained matching approaches are analyzed. Furthermore, a RANSAC based outlier removal for system combination is proposed. The proposed approach allows to match faces under partial occlusions, and even if they are not perfectly aligned or illuminated. Current approaches are sensitive to registration errors and usually rely on a very good initial alignment and illumination of the faces to be recognized. A grid-based and dense extraction of local features in combination with a block-based matching accounting for different viewpoint constraints is proposed, as interest-point based feature extraction approaches for face recognition often fail. The proposed SURF descriptors are compared to SIFT descriptors. Experimental results on the AR-Face and CMU-PIE database using manually aligned faces, unaligned faces, and partially occluded faces show that the proposed approach is robust and can outperform current generic approaches. © 2009. The copyright of this document resides with its authors.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Statistical pattern recognition and machine translation from 1988 to 1998: What has happened?

Statistical pattern recognition and machine translation from...

引用

8th International Workshop on pattern recognition in Information Systems, PRIS 2008;In Conjunction with ICEIS 2008

作者： Ney, Hermann Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany

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：