检索结果-内蒙古大学图书馆

The Journal of China Universities of Posts and Telecommunications 2008年第2期15卷 130-134页

作者： ZHAO Jian DONG Yuan ZHAO Xian-yu YANG Hao WANG Hai-la Laboratory of Pattern Recognition and Intelligent System Beijing Universityof Posts and Telecommunications Beijing 100876 China France Telecom Research and Development Center Beijing 100080 China

Speaker adaptive test normalization （ATnorm） is the most effective approach of the widely used score normalization in text-flldependent speaker verification, which selects speaker adaptive impostor cohorts with an extra development corpus in order to enhance the recognition performance. In this paper, an improved implementation of ATnorm that can offer overall significant advantages over the original ATnorm is presented. This method adopts a novel cross similarity measurement in speaker adaptive cohort model selection without an extra development corpus. It can achieve a comparable performance with the original ATnorm and reduce the computation complexity moderately. With the full use of the saved extra development corpus, the overall system performance can be improved significantly. The results are presented on NIST 2006 Speaker recognition Evaluation data corpora where it is shown that this method provides significant improvements in system performance, with relatively 14.4% gain on equal error rate （EER） and 14.6% gain on decision cost function （DCF） obtained as a whole.

关键词： speaker ATnorm score normalization cross similaritymeasurement speaker verification NIST speaker recognitionevaluation

来源：评论

学校读者我要写书评

暂无评论

Multi-class classifier of non-speech audio based on Fisher kernel

引用

Frontiers of Electrical and Electronic Engineering in China 2010年第1期5卷 72-76页

作者： Rongyan WANG Gang LIU Jun GUO Yu FANG Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and TelecommunicationsBeijing 100876China

Traditional multi-class classification methods based on Fisher kernel combine generative models such as Gaussian mixture models(GMMs)of all the classes ***,the combination generates high dimensional feature vectors and leads to large *** this paper,a new classification method is *** method adopts an intelligent feature space selection strategy by clustering similar Gaussian mixtures in order to reduce the feature *** classification experiments show that the proposed method is more accurate and effective with less computation compared with traditional methods.

关键词： Fisher kernel support vector machine(SVM) Gaussian mixture model(GMM) mixture clustering

来源：评论

学校读者我要写书评

暂无评论

Speech enhancement based on modified a priori SNR estimation

引用

Frontiers of Electrical and Electronic Engineering in China 2011年第4期6卷 542-546页

作者： Yu FANG Gang LIU Jun GUO Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and TelecommunicationsBeijing 100876China

To solve the frame delay problem and match the previous frame,Plapous et al.[IEEE Transactions on Audio,Speech,and Language Processing,2006,14(6):2098–2108]introduced a novel approach called two-step noise reduction(TSNR)technique to improve the performance of the speech enhancement ***,TSNR approach results in spectral peaks of short duration and the broken spectral outlier,which degrade the spectral characteristics of the *** solve this problem,a cepstral smoothing step is added in order to remove these spectral peaks brought by TSNR *** analysis shows that the proposed approach can effectively smooth the spectral peaks and keep the spectral outlier so as to protect the speech *** results also show that the proposed approach can bring significant improvement compared to decision-directed(DD)and TSNR approaches,especially in non-stationary noisy environments.

关键词： speech enhancement decision-directed(DD) two-step noise reduction(TSNR) signal-to-noise ratio(SNR)estimation

来源：评论

学校读者我要写书评

暂无评论

Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label Calibration

Learning Discriminative Representations for Open Relation Ex...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Wang, Shusen Duan, Bin Wu, Yanan Xu, Yajing Pattern Recognition & Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781955917766

Open relation extraction is the task to extract relational facts without pre-defined relation types from open-domain corpora. However, since there are some hard or semi-hard instances sharing similar context and entity information but belonging to different underlying relation, current OpenRE methods always cluster them into the same relation type. In this paper, we propose a novel method based on Instance Ranking and Label Calibration strategies (IRLC) to learn discriminative representations for open relation extraction. Due to lacking the original instance label, we provide three surrogate strategies to generate the positive, hard negative, and semi-hard negative instances for the original instance. Instance ranking aims to refine the relational feature space by pushing the hard and semi-hard negative instances apart from the original instance with different margins and pulling the original instance and its positive instance together. To refine the cluster probability distributions of these instances, we introduce a label calibration strategy to model the constraint relationship between instances. Experimental results on two public datasets demonstrate that our proposed method can significantly outperform the previous state-of-the-art methods. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction

RCL: Relation Contrastive Learning for Zero-Shot Relation Ex...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Wang, Shusen Zhang, Bosen Xu, Yajing Wu, Yanan Xiao, Bo Pattern Recognition & Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781955917766

Zero-shot relation extraction aims to identify novel relations which cannot be observed at the training stage. However, it still faces some challenges since the unseen relations of instances are similar or the input sentences have similar entities, the unseen relation representations from different categories tend to overlap and lead to errors. In this paper, we propose a novel Relation Contrastive Learning framework (RCL) to mitigate above two types of similar problems: Similar Relations and Similar Entities. By jointly optimizing a contrastive instance loss with a relation classification loss on seen relations, RCL can learn subtle difference between instances and achieve better separation between different relation categories in the representation space simultaneously. Especially in contrastive instance learning, the dropout noise as data augmentation is adopted to amplify the semantic difference between similar instances without breaking relation representation, so as to promote model to learn more effective representations. Experiments conducted on two well-known datasets show that RCL can significantly outperform previous state-of-the-art methods. Moreover, if the seen relations are insufficient, RCL can also obtain comparable results with the model trained on the full training set, showing the robustness of our approach. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Novel active learning sample evaluation method based on multi-level confusion networks

Novel active learning sample evaluation method based on mult...

引用

2010 2nd IEEE International Conference on Network Infrastructure and Digital Content, IC-NIDC 2010

作者： Chen, Wei Liu, Gang Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781424468546

Active Learning (AL) is designed to aid the labor-intensive process of training acoustic model for speech recognition. In AL, only the most informative training samples are selected for manual annotation. Thus, how to evaluate the unlabeled samples is worth researching. In this paper, we propose a unified framework to generate confusion networks of multiple levels including character, syllable and phone, and present a novel active learning sample evaluation method for Chinese acoustic modeling, posterior probabilities obtained from multi-level confusion networks are respectively adopted to evaluate the unlabeled samples. Our experiments show that compared with the widely used sample evaluation method using word posterior probability obtained from word confusion network, our proposed method can achieve satisfying performances. ©2010 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction 29

Cluster-aware Pseudo-Labeling for Supervised Open Relation E...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Duan, Bin Wang, Shusen Liu, Xingxian Xu, Yajing Pattern Recognition & Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Supervised open relation extraction aims to discover novel relations by leveraging supervised data of pre-defined relations. However, most existing methods do not achieve effective knowledge transfer from pre-defined relations to novel relations, they have difficulties generating high-quality pseudo-labels for unsupervised data of novel relations and usually suffer from the error propagation issue. In this paper, we propose a Cluster-aware Pseudo-Labeling (CaPL) method to improve the pseudo-labels quality and transfer more knowledge for discovering novel relations. Specifically, the model is first pre-trained with the pre-defined relations to learn the relation representations. To improve the pseudo-labels quality, the distances between each instance and all cluster centers are used to generate cluster-aware soft pseudo-labels for novel relations. To mitigate the catastrophic forgetting issue, we design the consistency regularization loss to make better use of the pseudo-labels and jointly train the model with both unsupervised and supervised data. Experimental results on two public datasets demonstrate that our proposed method achieves new state-of-the-arts performance © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A visualization algorithm for alarm association mining

A visualization algorithm for alarm association mining

引用

2009 IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC2009

作者： Xu, Qianfang Li, Chunguang Xiao, Bo Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781424448982

Currently those algorithms to mine the alarm association rules are limited to the minimal support, so that they can only obtain the association rules among the frequently occurring alarm events, furthermore, the rules couldn't be visual display. This paper provides a novel mining alarm correlation visualization algorithm based on the non-linear reduced-feature mapping. The algorithm firstly projects the alarms on multidimensional space according to co-occurrence strength of the alarms, and then reduces the dimensions of the space, finally provides the relationship of the alarms to user with visualization. Experimental results based on synthetic and real datasets demonstrated that this algorithm not only discovered correlation among alarms, but also acquired the fault in the telecommunications network based on the graph transformation. ©2009 IEEE.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning for automatic audio events annotation using TSVM

Semi-supervised learning for automatic audio events annotati...

引用

2010 International Conference on Computer Application and system Modeling, ICCASM 2010

作者： Wang, Rongyan Liu, Gang Guo, Jun Ma, Zhenxin Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing 100876 China

ISBN: (纸本)9781424472369

Most previous approaches to automatic audio events (AEs) annotation are based on supervised learning which relies on the availability of a labeled corpus to train classification models. However, instance annotation is often difficult, expensive, and time consuming. In this paper, we apply semi- supervised learning with transductive Support Vector Machine (TSVM) algorithm to automatic AEs annotation. Besides, considering about the presence of outliers which degrade the generalization and the classification performance, we propose a confidence-based method for samples selection. In our experiments based on the melodrama Friends corpus, the proposed method can effectively use unlabeled data to improve the classification performance with only a small amount of the labeled data.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Sparse feature representation for visual tracking

Sparse feature representation for visual tracking

引用

2012 International Conference on systems and Informatics, ICSAI 2012

作者： Liu, Yifei Han, Zhenjun Ye, Qixiang Jiao, Jianbin Li, Ce Pattern Recognition and Intelligent System Development Laboratory Graduate University Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781467301992

In this paper, a novel sparse feature representation method for object tracking is proposed. The method is on the observation that a tracked object can be dynamically and compactly represented by a few features (sparse representation) from a large feature set (the improved histogram of oriented gradient and color, HOGC). Based on the HOGC features, the sparse representation can be learned online from the constructed training samples during the tracking procedure by exploiting the L1-norm minimization principle, which can also be called feature selection procedure, ensuring the tracking can adapt to the appearance variations of either foreground or background. Experiments with comparisons demonstrate the effectiveness of the proposed method. © 2012 IEEE.

关键词： Feature Selection

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：