检索结果-内蒙古大学图书馆

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

作者： Maina, Samuel C. Bryant, Reginald E. Ogallo, William O. Varshney, Kush R. Speakman, Skyler Cintas, Celia Walcott-Bryant, Aisha Samoilescu, Robert-Florian Weldemariam, Komminist IBM Res Nairobi Kenya Univ Politehn Bucuresti Bucharest Romania

ISBN: (纸本)9781509066315

We investigate the effect of variational autoencoder (VAE) based data anonymization and its ability to preserve anomalous subgroup properties. We present a Utility Guaranteed Deep Privacy (UGDP) system which casts existing anomalous pattern detection methods as a new utility measure for data synthesis. UGDP's approach shows that properties of an anomalous subset of records, identified in the original data set, are preserved through the anonymization of a VAE. This is despite the newly generated records being completely synthetic. More specifically, the Bias-Scan algorithm identifies a subgroup of records that are consistently over- (or under-) risked by a black-box classifier as an area of 'poor fit'. This scanning process is applied on both pre- and post- VAE synthesized data. The areas of poor fit (i.e. anomalous records) persist in both settings. We evaluate our approach using publicly available datasets from the financial industry. Our evaluation confirmed that the approach is able to produce synthetic datasets that preserved a high level of subgroup differentiation as identified initially in the original dataset. Such a distinction was maintained while having distinctly different records between the synthetic and original dataset.

关键词： privacy bias anonymization variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Learning to Model the Grasp Space of an Underactuated Robot Gripper Using variational autoencoder

引用

IFAC-PapersOnLine 2021年第7期54卷 523-528页

作者： Clément Rolinat Mathieu Grossard Saifeddine Aloui Christelle Godin Université Paris-Saclay CEA List F-91120 Palaiseau France Université Grenoble Alpes CEA Leti F-38000 Grenoble France

Grasp planning and most specifically the grasp space exploration is still an open issue in robotics. This article presents a data-driven oriented methodology to model the grasp space of a multi-fingered adaptive gripper for known objects. This method relies on a limited dataset of manually specified expert grasps, and uses variational autoencoder to learn grasp intrinsic features in a compact way from a computational point of view. The learnt model can then be used to generate new non-learnt gripper configurations to explore the grasp space.

关键词： multi-fingered gripper grasp space exploration variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Optimization Algorithm of Time Synchronization Network Monitoring Based on variational autoencoder 5

Optimization Algorithm of Time Synchronization Network Monit...

引用

5th International Conference on Computational Intelligence and Applications (ICCIA)

作者： Lv, Bo Pan, Feng Miao, Xinyu Hu, Changjun China Acad Informat & Commun Inst Technol & Stand Beijing Peoples R China

ISBN: (纸本)9781728160429

In this paper an optimization algorithm for time synchronization in telecommunication network is proposed based on VAE(variational Auto Encoder)framework. Firstly features are represented in latent space under proposed framework while performance of synchronization network is measured and evaluated. Secondly optimization algorithm is further designed with which feature of abnormal samples and benchmark are adaptively merged for smooth adjustment with low risk in practical network operation. Meanwhile considering the characteristics as domain knowledge of synchronization network, a novel metric is adopted to reduce the fluctuation of adjustment. The simulation results verified that performance of synchronization network is significantly improved by optimization templates reconstructed through decoding part of VAE model. It is implied that prior knowledge of synchronization in latent space is introduced with certain interpret-ability for assessment of monitoring performance while optimization adjustment can be properly operated through novel metric proposed in this algorithm.

关键词： telecommunication time synchronization machine learning variational autoencoder optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A variational autoencoder Approach for Speech Signal Separation 12th

A Variational Autoencoder Approach for Speech Signal Separat...

引用

12th International Conference on Computational Collective Intelligence (ICCCI)

作者： Do, Hao D. Tran, Son T. Chau, Duc T. Univ Sci Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam OLLI Technol JSC Ho Chi Minh City Vietnam

ISBN: (纸本)9783030630065;9783030630072

Speech separation plays an important role in a speech-related system since it can denoise, extract, and enhance speech signals. In recent years, many methods are proposed to separate the human voice of noise and other sounds. To separate the speech from a complicated signal, we propose a more powerful method by using a VAE model and then postprocessing with a bandpass filter. This combination can use to extract the original human speech in the mixture with not only high-frequency noise but also many different sounds. Our approach can be flexibly applied for the new background sounds.

关键词： Bandpass filter variational autoencoder Frequency domain Speech separation

来源：评论

学校读者我要写书评

暂无评论

VAE-BRIDGE: variational autoencoder Filter for Bayesian Ridge Imputation of Missing Data

VAE-BRIDGE: Variational Autoencoder Filter for Bayesian Ridg...

引用

International Joint Conference on Neural Networks (IJCNN) held as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Pereira, Ricardo Cardoso Abreu, Pedro Henriques Rodrigues, Pedro Pereira Univ Coimbra Ctr Informat & Syst Dept Informat Engn Coimbra Portugal Univ Porto Ctr Hlth Technol & Serv Res Porto Portugal

ISBN: (纸本)9781728169262

The missing data issue is often found in real-world datasets and it is usually handled with imputation strategies that replace the missing values with new data. Recently, generative models such as variational autoencoders have been applied for this imputation task. However, they were always used to perform the entire imputation, which has presented limited results when comparing to other state-of-the-art methods. In this work, a new approach called variational autoencoder Filter for Bayesian Ridge Imputation is introduced. It uses a variational autoencoder at the beginning of the imputation pipeline to filter the instances that are later fitted to a Bayesian ridge regression used to predict the new values. The approach was compared to four state-of-the-art imputation methods using 10 datasets from the healthcare context covering clinical trials, all injected with missing values under different rates. The proposed approach significantly outperformed the remaining methods in all settings, achieving an overall improvement between 26% and 67%.

关键词： missing data variational autoencoder bayesian ridge data imputation healthcare data

来源：评论

学校读者我要写书评

暂无评论

Improved variational autoencoder Anomaly Detection in Time Series Data

Improved Variational Autoencoder Anomaly Detection in Time S...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Yokkampon, Umaporn Chumkamon, Sakmongkon Mowshowitz, Abbe Fujisawa, Ryusuke Hayashi, Eiji Kyushu Inst Technol Dept Comp Sci & Syst Engn Fukuoka Japan CUNY City Coll Dept Comp Sci New York NY USA

ISBN: (纸本)9781728185262

Uncertainty in observations about the state of affairs is unavoidable, and generally undesirable, so we are motivated to try to minimize its effect on data analysis. Detection of anomalies in data has become an important research area. In this paper, we propose a novel approach to anomaly detection based on the variational autoencoder method with a Mish activation function and a Negative Log-Likelihood loss function. The proposed method is validated with ten standard datasets, comparing performance on each of the various activation functions and loss functions. Experimental results show that our proposed method offers an improvement over existing methods. Statistical properties (i.e., F1 score, AUC, and ROC) of the method are also examined in light of the experimental results.

关键词： Anomaly Detection variational autoencoder Time Series Data Activation Functions Loss Functions

来源：评论

学校读者我要写书评

暂无评论

VAEPP: variational autoencoder with a Pull-Back Prior 27th

VAEPP: Variational Autoencoder with a Pull-Back Prior

引用

27th International Conference on Neural Information Processing

作者： Chen, Wenxiao Liu, Wenda Cai, Zhenting Xu, Haowen Pei, Dan Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China Beijing Natl Res Ctr Informat Sci & Technol BNRis Beijing Peoples R China

ISBN: (纸本)9783030638351;9783030638368

Many approaches to training generative models by distinct training objectives have been proposed in the past. variational autoencoder (VAE) is an outstanding model of them based on log-likelihood. In this paper, we propose a novel learnable prior, Pull-back Prior, for VAEs by adjusting the density of the prior through a discriminator that can assess the quality of data. It involves the discriminator from the theory of GANs to enrich the prior in VAEs. Based on it, we propose a more general framework, VAE with a Pull-back Prior (VAEPP), which uses existing techniques of VAEs and WGANs, to improve the log-likelihood, quality of sampling and stability of training. In MNIST and CIFAR-10, the log-likelihood of VAEPP outperforms models without autoregressive components and is comparable to autoregressive models. In MNIST, Fashion-MNIST, CIFAR-10 and CelebA, the FID of VAEPP is comparable to GANs and SOTA of VAEs.

关键词： variational autoencoder Deep generative model Adversarial training

来源：评论

学校读者我要写书评

暂无评论

MULTI-SPEAKER AND MULTI-DOMAIN EMOTIONAL VOICE CONVERSION USING FACTORIZED HIERARCHICAL variational autoencoder

MULTI-SPEAKER AND MULTI-DOMAIN EMOTIONAL VOICE CONVERSION US...

引用

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

作者： Elgaar, Mohamed Park, Jungbae Lee, Sang Wan Korea Adv Inst Sci & Technol Daejeon South Korea Humelo Inc Daejeon South Korea KAIST Inst Artificial Intelligence Daejeon South Korea

ISBN: (纸本)9781509066315

Due to the complexity of emotional features, there has been limited success in emotional voice conversion. One major challenge is that conversion between more than two kinds of emotions often accompanies distortion of voice signal. The factorized hierarchical variational autoencoder (FHVAE) [1] was previously shown to have an ability, called sequence-level regularization, to generate disentangled representations of both sequence-level (such as speaker identity) and segment-level features. This study exploits the FHVAE pipeline to produce disentangled representations of emotion, making it possible to greatly facilitate emotional voice conversion. We propose three versions of algorithms for improving the quality of disentangled representation and audio synthesis. We conducted three mean opinion score (MOS) surveys to assess the performance of our models in terms of 1) speaker's voice preservation, 2) emotion conversion, and 3) audio naturalness.

关键词： Emotional Voice Conversion variational autoencoder Disentangled Representation Style Transfer

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Deep Learning for Fault Detection on Spacecraft Using Improved variational autoencoder

Unsupervised Deep Learning for Fault Detection on Spacecraft...

引用

Chinese Automation Congress (CAC)

作者： Xiang, Gang Tao, Ran Peng, Yu Tian, Kun Qu, Chen Beihang Univ Natl Key Lab Aerosp Intelligent Control Beijing Aerosp Automat Control Inst Sch Automat Sci & Elect Engn Beijing Peoples R China Beijing Aerosp Automat Control Inst Natl Key Lab Aerosp Intelligent Control Beijing Peoples R China

ISBN: (纸本)9781728176871

Fault detection is important for improving the reliability of spacecraft, ensuring the long-term stable operation, and reducing the economic loss caused by failure. In order to solve the problems such as the large amount of test data, the scarcity of fault data samples and the real-time requirements in the field of spacecraft fault detection, an improved unsuperyised deep learning algorithm based on variational autoencoder (VAE) is proposed. The algorithm adopts Gated Recurrent Unit (GRU) based recurrent neural networks as encoder to automatically extract features of input data, and then uses VAE to learn the correlation features of multiple test data. The proposed network, trained only on the normal training dataset, is a typical unsupervised method which could learn features and reconstruct the data on the training set with a small loss. Once the reconstruction loss of the input data is larger than the pre-set threshold, the corresponding input data is considered as fault data. Experiments show that the proposed method is feasible and can effectively detect faults.

关键词： fault detection gated recurrent unit variational autoencoder deep learning spacecraft

来源：评论

学校读者我要写书评

暂无评论

Laughter synthesis: A comparison between variational autoencoder and autoencoder 5

Laughter synthesis: A comparison between Variational autoenc...

引用

5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

作者： Mansouri, Nadia Lachiri, Zied Tunis El Manar Univ Signal Image & Informat Technol Res Lab LR SITI Natl Engn Sch Tunis ENIT Tunis Tunisia

ISBN: (数字)9781728175133

ISBN: (纸本)9781728175133

Laughter is one of the most famous non verbal sounds that human produce since birth, it conveys messages about our emotional state. These characteristics make it an important sound that should be studied in order to improve the human-machine interactions. In this paper we investigate the audio laughter generation process from its acoustic features. This suggested process is considered as an analysis-transformation-synthesis benchmark based on unsupervised dimensionality reduction techniques: The standard autoencoder (AE) and the variational autoencoder (VAE). Therefore, the laughter synthesis methodology consists of transforming the extracted high-dimensional log magnitude spectrogram into a low-dimensional latent vector. This latent vector contains the most valuable information used to reconstruct a synthetic magnitude spectrogram that will be passed through a specific vocoder to generate the laughter waveform. We systematically, exploit the VAE to create new sound (speech-laugh) based on the interpolation process. To evaluate the performance of these models two evaluation metrics were conducted: objective and subjective evaluations.

关键词： Laughter audio generation variational autoencoder autoencoder interpolation objective and subjective evaluation

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：