检索结果-内蒙古大学图书馆

Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in variational autoencoder Based Voice Conversion

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2020年第4期4卷 468-479页

作者： Huang, Wen-Chin Luo, Hao Hwang, Hsin-Te Lo, Chen-Chou Peng, Yu-Huai Tsao, Yu Wang, Hsin-Min Acad Sinica Inst Informat Sci Taipei 11529 Taiwan Nagoya Univ Grad Sch Informat Nagoya Aichi 4648601 Japan Acad Sinica Res Ctr Informat Technol Inst Informat Sci Taipei 11529 Taiwan

An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this article, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and acid an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can he enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods.

关键词： Voice conversion unsupervised learning disentangled representation variational autoencoder adversarial learning cross domain features

来源：评论

学校读者我要写书评

暂无评论

Self-adversarial variational autoencoder with spectral residual for time series anomaly detection

引用

NEUROCOMPUTING 2021年 458卷 349-363页

作者： Liu, Yunxiao Lin, Youfang Xiao, QinFeng Hu, Ganghui Wang, Jing Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China Beijing Key Lab Traff Data Anal & Min Beijing Peoples R China CAAC Key Lab Intelligent Passenger Serv Civil Avi Beijing Peoples R China

Detecting anomalies accurately in time series data has been receiving considerable attention due to its enormous potential for a wide array of applications. Numerous unsupervised anomaly detection methods for time series have been developed because of the difficulty of obtaining accurate labels. However, most existing unsupervised approaches suffer from the problem of anomaly contamination, which results in models that are unable to learn the normal pattern well and further deteriorate the performance of detection methods. To this end, a novel unsupervised method, called Self-adversarial variational autoencoder with Spectral Residual (SaVAE-SR), is introduced for time series anomaly detection in this paper. The SaVAE-SR first produces labels for unlabeled training data using the spectral residual technique to identify the most critical anomalies. A VAE model with a modified loss that can leverage label information to remove the influence of anomalous points is then trained in a self-adversarial manner, enabling the model to self-evaluate the learning of complex data distribution and improve itself accordingly. Specifically, the encoder acts as an encoder to approximate the posterior of latent variables and as a discriminator to evaluate the generative ability of the generator and improve itself accordingly. The generator is trained to capture the underlying data distribution and attempts to produce real samples to deceive the discriminator. The encoder and generator of the model compete with each other just like the behavior of GANs but work together under the theoretical framework of VAEs. As a result, the SaVAE-SR model combines the respective strengths of the VAE and adversarial training but does not require an additional discriminator, which makes the whole model very compact. Extensive experiments on five datasets demonstrate the superiority of the proposed method over the existing state-of-the-art methods. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Anomaly detection Adversarial training Spectral residual Time series variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Case2vec: joint variational autoencoder for case text embedding representation

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2021年第9期12卷 2517-2528页

作者： Song, Ran Gao, Shengxiang Yu, Zhengtao Zhang, Yafei Zhou, Gaofeng Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming 650500 Yunnan Peoples R China

The embedding representation of the case text represent text as vector which consist information of original texts abundantly. Text embedding representation usually uses text statistical features or content features alone. However, case texts have characteristics that include similar structure, repeated words, and different text lengths. And the statistical feature or content feature cannot represent case text efficiently. In this paper, we propose a joint variational autoencoder (VAE) to represent case text embedding representation. We consider the statistical features and content features of case texts together, and use VAE to align the two features into the same space. We compare our representations with existing methods in terms of quality, relationship, and efficiency. The experiment results show that our method has achieved good results, which have higher performance than the model using single feature.

关键词： Embedding representation Statistical feature Content feature variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Process monitoring using variational autoencoder for high-dimensional nonlinear processes

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2019年 83卷 13-27页

作者： Lee, Seulki Kwak, Mingu Tsui, Kwok-Leung Kim, Seoung Bum Korea Univ Sch Ind Management Engn 145 Anam Ro Seoul 02841 South Korea City Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong 999077 Peoples R China

In many industries, statistical process monitoring techniques play a key role in improving processes through variation reduction and defect prevention. Modern large-scale industrial processes require appropriate monitoring techniques that can efficiently address high-dimensional nonlinear processes. Such processes have been successfully monitored with several latent variable-based methods. However, because these monitoring methods use Hotelling's T-2 statistics in the reduced space, a normality assumption underlies the construction of these tools. This assumption has limited the use of latent variable-based monitoring charts in both nonlinear and nonnormal situations. In this study, we propose a variational autoencoder (VAE) as a monitoring method that can address both nonlinear and nonnormal situations in high-dimensional processes. VAE is appropriate for T-2 charts because it causes the reduced space to follow a multivariate normal distribution. The effectiveness and applicability of the proposed VAE-based chart were demonstrated through experiments on simulated data and real data from a thin-film-transistor liquid-crystal display process.

关键词： Statistical process monitoring variational autoencoder High-dimensional process Nonlinear process Multivariate control chart

来源：评论

学校读者我要写书评

暂无评论

Infer-AVAE: An attribute inference model based on adversarial variational autoencoder

引用

NEUROCOMPUTING 2022年 483卷 105-115页

作者： Zhou, Yadong Ding, Zhihao Liu, Xiaoming Shen, Chao Tong, Lingling Guan, Xiaohong Xi An Jiao Tong Univ Fac Elect & Informat Engn MOE KLINNS Lab Xian 710049 Shaanxi Peoples R China Natl Comp Network Emergency Response Tech Team Beijing Peoples R China Tsinghua Univ Ctr Intelligent & Networked Syst Beijing 100084 Peoples R China Tsinghua Univ TNLIST Lab Beijing 100084 Peoples R China

User attributes, such as gender and education, face severe incompleteness in social networks. Attribute inference aims to infer users' missing attribute labels based on observed data to make this valuable data usable for downstream tasks like user profiling and personalized recommendation. Recently, variational autoencoder (VAE), an end-to-end deep generative model, has shown promising performance by handling the problem in a semi-supervised way. However, VAEs can easily suffer from over-fitting and over-smoothing when applied to attribute inference. Specifically, VAE implemented with multi-layer perceptron (MLP) can only reconstruct input data but fail to infer missing parts. While using the trending graph neural networks (GNNs) as encoder has the problem that GNNs aggregate redundant information from the neighborhood and generate indistinguishable user representations, known as over-smoothing. In this paper, we propose an attribute Inference model based on Adversarial VAE (Infer-AVAE) to cope with these issues. Specifically, to overcome over-smoothing, Infer-AVAE unifies MLP and GNNs in the encoder to learn positive and negative latent representations respectively. Meanwhile, an adversarial network is trained to distinguish the two representations, and GNNs are trained to aggregate less noise for more robust representations through adversarial training. Finally, to relieve over-fitting, mutual information constraint is introduced as a regularizer for the decoder to make better use of auxiliary information in representations and generate outputs not limited by observations. We evaluate our model on four real world social network datasets, and experimental results demonstrate that our model averagely outperforms baselines by 7.0% in accuracy. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Social network Attribute inference Graph neural network variational autoencoder Adversarial training Mutual information

来源：评论

学校读者我要写书评

暂无评论

Emotion-Regularized Conditional variational autoencoder for Emotional Response Generation

引用

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 2023年第1期14卷 842-848页

作者： Ruan, Yu-Ping Ling, Zhen-Hua Natl Univ Def Technol Hefei 230031 Peoples R China Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei 230027 Peoples R China

This article presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based emotional response generation, emotion labels are simply used as additional conditions in prior, posterior and decoder networks. Considering that emotion styles are naturally entangled with semantic contents in the language space, the Emo-CVAE model utilizes emotion labels to regularize the CVAE latent space by introducing an extra emotion prediction network. In the training stage, the estimated latent variables are required to predict the emotion labels and token sequences of the input responses simultaneously. Experimental results show that our Emo-CVAE model can learn a more informative and structured latent space than a conventional CVAE model and output responses with better content and emotion performance than baseline CVAE and sequence-to-sequence (Seq2Seq) models.

关键词： Training Emotional responses Testing Decoding Earth Observing System Bit error rate Semantics Emotional response generation latent variables variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

RUL Prediction Using a Fusion of Attention-Based Convolutional variational autoencoder and Ensemble Learning Classifier

引用

IEEE TRANSACTIONS ON RELIABILITY 2023年第1期72卷 106-124页

作者： Remadna, Ikram Terrissa, Labib Sadek Al Masry, Zeina Zerhouni, Noureddine Univ Biskra Dept Comp Sci LINFI Lab Biskra 07000 Algeria Univ Bourgogne Franche Comte CNRS FEMTO ST Inst ENSMM F-25044 Besancon France

Predicting the remaining useful life (RUL) is a critical step before the decision-making process and developing maintenance strategies. As a result, it is frequently impacted by uncertainty in a practical context and may cause issues. This article proposes a new hybrid deep architecture that predicts when an in-service machine will fail to overcome the latter problem, allowing for an improved data analysis and dimensionality reduction capability providing better spatial distributions of features and increasing interpretability. A deep convolutional variational autoencoder with an attention mechanism (ACVAE) has been developed and tested using the aero-engine C-MAPSS dataset. We defined two adapted threshold settings (alpha 1, alpha 2) by analyzing the spatial distribution and minimizing the overlapping area between the degradation classes. To reduce the conflict zone, we used the soft voting classifier. The performance of our visual explainable deep learning model has reached a higher level of accuracy compared with previous existing models.

关键词： Feature extraction Degradation Computer architecture Estimation Decoding Prognostics and health management Visualization Attention mechanism data visualization deep learning prognostics and health management variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Topic-word-constrained sentence generation with variational autoencoder

引用

PATTERN RECOGNITION LETTERS 2022年 160卷 148-154页

作者： Song, Tianbao Sun, Jingbo Liu, Xin Song, Jihua Peng, Weiming Beijing Technol & Business Univ Sch Comp Sci & Engn Beijing 100048 Peoples R China Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China 15th Res Inst China Elect Technol Grp Corp Beijing 100083 Peoples R China

We propose a topic-word-constrained sentence-generation model with a variational autoencoder and convolutional neural network. It can generate sentences conditioned on a given topic distribution and a certain word. Unlike the vanilla variational autoencoder that assumes a standard Gaussian prior for the latent code, our model specifies the prior for the topic latent code as multiple Gaussian distributions, where each Gaussian distribution corresponds to a topic vector parameterized by a convolutional neural topic model. For word constraints, the decoder in the variational autoencoder generates sentences back-ward and forward starting from a given word. The topic latent space is arranged by the similarity of topic vectors, and the topic latent code restricts the sentence latent code through a loss term, through which expanded semantically meaningful latent spaces can be learned and provide topic guidance while gener-ating sentences. Experimental results show that our model can generate coherent and diverse sentences related to given topics and words, while also avoiding the Kullback-Leibler divergence collapse problem. Moreover, it outperforms alternative approaches in terms of sentence reconstruction, latent space prop-erty and the quality, diversity, and topic controllability of generated sentences.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Natural language generation variational autoencoder Constrained sentence generation

来源：评论

学校读者我要写书评

暂无评论

Flight maneuver intelligent recognition based on deep variational autoencoder network

引用

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING 2022年第1期2022卷 1-23页

作者： Tian, Wei Zhang, Hong Li, Hui Xiong, Yuan Jiangxi Hongdu Aviat Ind Grp Co Ltd Nanchang 330001 Jiangxi Peoples R China Naval Aviat Univ Yantai 264000 Peoples R China

The selection and training of aircraft pilots has high standards, long training cycles, high resource consumption, high risk, and high elimination rate. It is the particularly urgent and important requirement for the current talent training strategy of national and military to increase efficiency and speed up all aspects of pilot training, reduce the training cycle and reduce the elimination rate. To this end, this paper uses deep variational auto-encoder network and adaptive dynamic time warping algorithms as support to explore the establishment of an integrated evaluation system for flight maneuver recognition and quality evaluation, solve the industry difficulty faced by current flight training data mining applications, and achieve accurate recognition and reliable quality evaluation of flight regimes under the background of high mobility. It will fully explore the benefits of existing airborne flight data for military trainee pilots, support the personalized and accurate training of flight talents, and reduce the rate of talent elimination.

关键词： variational autoencoder Flight maneuver recognition Flight quality evaluation Dynamic time warping Deep neural network

来源：评论

学校读者我要写书评

暂无评论

Deep Nonnegative Matrix Factorization Using a variational autoencoder With Application to Single-Cell RNA Sequencing Data

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第2期20卷 883-893页

作者： Jee, Dong Jun Kong, Yixin Chun, Hyonho Korea Adv Inst Sci & Technol Dept Math Sci KR-34141 Daejeon South Korea Boston Univ Dept Math & Stat Boston MA 02134 USA

Single-cell RNA sequencing is used to analyze the gene expression data of individual cells, thereby adding to existing knowledge of biological phenomena. Accordingly, this technology is widely used in numerous biomedical studies. Recently, the variational autoencoder has emerged and has been adopted for the analysis of single-cell data owing to its high capacity to manage large-scale data. Many different variants of the variational autoencoder have been applied, and have yielded superior results. However, because it is nonlinear, the model does not provide parameters that can be used to explain the underlying biological patterns. In this paper, we propose an interpretable nonnegative matrix factorization method that decomposes parameters into those shared across cells and those that are cell-specific. Effective nonlinear dimension reduction was achieved via a variational autoencoder applied to the cell-specific parameters. In addition to achieving nonlinear dimension reduction, our model could estimate the cell-type-specific gene expression. To improve the estimation accuracy, we introduced log-regularization, which reflects the single-cell property. Overall, our approach displayed excellent performance in a simulation study and in real data analyses, while maintaining good biological interpretability.

关键词： Dimensionality reduction Matrix decomposition Neural networks Data models Decoding Analytical models Sequential analysis Deep neural networks nonlinear dimension reduction nonnegative matrix factorization single -cell RNA sequencing data variational autoencoder

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

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

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：