发布求助
文献互助 智能选刊 最新文献

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)最新文献

筛选
英文 中文
Explainable Deep Learning Detection of Gaussian Propeller Noise with Unknown Signal-to-Noise Ratio 未知信噪比高斯螺旋桨噪声的可解释深度学习检测
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596566
M. Thomas, Fillatre Lionel, Deruaz-Pepin Laurent
{"title":"Explainable Deep Learning Detection of Gaussian Propeller Noise with Unknown Signal-to-Noise Ratio","authors":"M. Thomas, Fillatre Lionel, Deruaz-Pepin Laurent","doi":"10.1109/mlsp52302.2021.9596566","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596566","url":null,"abstract":"Due to its need for robustness and reliability, underwater target detection is a challenging task for deep learning applications. Though many attempts were made to deal with this problem using expert features, few works assessed the benefit of designing deep raw waveform architecture despite its performance in other domains. This paper is focused on explainable raw waveform based neural network for underwater propeller detection. To this purpose, we design a class of Bayes explainable deep neural networks that contains neural networks whose architecture matches the structure of the optimal Bayes detector. This class is derived from a realistic acoustic model of underwater propeller noise. It is established that the approximation error of our class is as small as desired. We also show that this class can be efficiently implemented as a convolutional neural network. Numerical simulations study the risk and explainability of our class compared to a usual convolutional neural network.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131301169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
A Placement Angle Detection Method of Recyclable Object for Garbage Power Generation 垃圾发电中可回收物放置角度检测方法
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596431
Y. Cai, Mengwei Chen, Yifei Feng, Zheng Ming
{"title":"A Placement Angle Detection Method of Recyclable Object for Garbage Power Generation","authors":"Y. Cai, Mengwei Chen, Yifei Feng, Zheng Ming","doi":"10.1109/mlsp52302.2021.9596431","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596431","url":null,"abstract":"With the rapid development of China's economy, the number of population increases year by year, and the municipal solid waste (MSW) increases rapidly. Garbage incineration power generation can realize the harmlessness and resource of domestic garbage, thus realize the green construction of our country and promote the further development of our economy. In this paper, Yolo network is used to detect household garbage, improved on the basis of the original network to solve the problem that Yolo network can not detect the the angle. And a recyclable garbage dataset containing the angle of the object is constructed.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129903655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A General Parametrization Framework for Pairwise Markov Models: An Application to Unsupervised Image Segmentation 成对马尔可夫模型的通用参数化框架:在无监督图像分割中的应用
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596395
H. Gangloff, Katherine Morales, Y. Petetin
{"title":"A General Parametrization Framework for Pairwise Markov Models: An Application to Unsupervised Image Segmentation","authors":"H. Gangloff, Katherine Morales, Y. Petetin","doi":"10.1109/mlsp52302.2021.9596395","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596395","url":null,"abstract":"Probabilistic graphical models such as Hidden Markov models have found many applications in signal processing. In this paper, we focus on a particular extension of these models, the Pairwise Markov models. We propose a general parametrization of the probability distributions describing the Pairwise Markov models which enables us to combine them with recent architectures from machine learning such as deep neural networks. In order to evaluate the power of these combined architectures, we focus on the unsupervised image segmentation problem which is particularly challenging and we propose a new parameter estimation algorithm. We show that our models with their associated estimation algorithm outperforms the classical probabilistic models for the task of unsupervised image segmentation.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122493980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Adaptive Normalized LMP Estimation for Graph Signal Processing 图信号处理中的自适应归一化LMP估计
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596181
Yi Yan, Radwa Adel, E. Kuruoğlu
{"title":"Adaptive Normalized LMP Estimation for Graph Signal Processing","authors":"Yi Yan, Radwa Adel, E. Kuruoğlu","doi":"10.1109/mlsp52302.2021.9596181","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596181","url":null,"abstract":"We propose an adaptive normalized least mean pth power (GNLMP) algorithm for graph signal processing (GSP), which estimates sampled graph signals under impulsive noise. Compared to the recently introduced adaptive GSP least mean pth power (GLMP) algorithm, the GNLMP algorithm reduces the number of iterations to converge to a steady graph signal. Different from adaptive GSP normalized least mean square (GNLMS) algorithm, the GNLMP algorithm has the ability to reconstruct a graph signal that is corrupted by non-Gaussian noise with heavy-tailed characteristics. Simulations show the performance of the GNLMP algorithm in estimating steady-state and time-varying graph signals, utilizing spectral properties such as bandlimitedness and sampling, faster and more robust in comparison to GLMP and GNLMS.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126565275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective 基于自监督目标分解层次变分自编码器的解纠缠语音表示学习
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/MLSP52302.2021.9596320
Yuying Xie, Thomas Arildsen, Z. Tan
{"title":"Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective","authors":"Yuying Xie, Thomas Arildsen, Z. Tan","doi":"10.1109/MLSP52302.2021.9596320","DOIUrl":"https://doi.org/10.1109/MLSP52302.2021.9596320","url":null,"abstract":"Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents a way to disentangle a speech signal into sequential-level and segmental-level features, which represent speaker identity and speech content information, respectively. As a self-supervised objective, autoregressive predictive coding (APC), on the other hand, has been used in extracting meaningful and transferable speech features for multiple downstream tasks. Inspired by the success of these two representation learning methods, this paper proposes to integrate the APC objective into the FHVAE framework aiming at benefiting from the additional self-supervision target. The main proposed method requires neither more training data nor more computational cost at test time, but obtains improved meaningful representations while maintaining disentanglement. The experiments were conducted on the TIMIT dataset. Results demonstrate that FHVAE equipped with the additional self-supervised objective is able to learn features providing superior performance for tasks including speech recognition and speaker recognition. Furthermore, voice conversion, as one application of disentangled representation learning, has been applied and evaluated. The results show performance similar to baseline of the new framework on voice conversion.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130462191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Caesynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders synth:实时音色插值和音高控制与条件自编码器
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596414
Aaron Valero Puche, Sukhan Lee
{"title":"Caesynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders","authors":"Aaron Valero Puche, Sukhan Lee","doi":"10.1109/mlsp52302.2021.9596414","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596414","url":null,"abstract":"In this paper, we present a novel audio synthesizer, CAESynth, based on a conditional autoencoder. CAESynth synthesizes timbre in real-time by interpolating the reference sounds in their shared latent feature space, while controlling a pitch independently. We show that training a conditional autoen-coder based on accuracy in timbre classification together with adversarial regularization of pitch content allows timbre distribution in latent space to be more effective and stable for timbre interpolation and pitch conditioning. The proposed method is applicable not only to creation of musical cues but also to exploration of audio affordance in mixed reality based on novel timbre mixtures with environmental sounds. We demonstrate by experiments that CAESynth achieves smooth and high-fidelity audio synthesis in real-time through timbre interpolation and independent yet accurate pitch control for musical cues as well as for audio affordance with environmental sound. A Python implementation along with some generated samples are shared online.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131265672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Singing Fundamental Frequency Contour Generation Using Generalized Command-Response Model and Score-Conditional Variational Autoencoder 基于广义命令响应模型和分数条件变分自编码器的歌唱基频轮廓生成
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596428
Shogo Seki, Haruka Taga, T. Toda
{"title":"Singing Fundamental Frequency Contour Generation Using Generalized Command-Response Model and Score-Conditional Variational Autoencoder","authors":"Shogo Seki, Haruka Taga, T. Toda","doi":"10.1109/mlsp52302.2021.9596428","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596428","url":null,"abstract":"This paper proposes a method for achieving physically motivated and interpretable control of fundamental frequency (F0) contour generation in singing aid systems for laryngectomees. Recently proposed variational autoencoder (VAE)-based method, VAE-SPACE, has successfully generated singing F0 contours from musical scores. However, VAE-SPACE can generate physically deviated F0 contours. Moreover, to represent fluctuations in F0 contours, VAE-SPACE requires manual adjustment of noise components used as the input with musical scores. To address these issues, the proposed method 1) introduces a generalized command-response (GCR) model to represent an F0 contour as an approximation of a physical F0 production mechanism, and 2) employs a conditional VAE (CVAE) to treat musical scores and the noise components separately. The experimental results reveal that the proposed method achieves comparable performance as VAE-SPACE without the manual adjustment of noise components and makes it possible to control F0 contours more intuitively by using the trained GCR model.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131655194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Adversarial Perturbation Attacks on Nested Dichotomies Classification Systems 嵌套二分类系统的对抗摄动攻击
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596336
Ismail R. Alkhouri, Alvaro Velasquez, George K. Atia
{"title":"Adversarial Perturbation Attacks on Nested Dichotomies Classification Systems","authors":"Ismail R. Alkhouri, Alvaro Velasquez, George K. Atia","doi":"10.1109/mlsp52302.2021.9596336","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596336","url":null,"abstract":"The study of robustness of deep classifiers has exposed their vulnerability to perturbation attacks. Prior work has largely focused on adversarial attacks targeting one-stage-classifiers. By contrast, here we investigate the susceptibility of Nested Dichotomies Classifiers (NDCs), which decompose a multiclass problem into a collection of binary ones, to such types of individual attacks. First, we show that the overall regret of an NDC is the sum of regrets of the binary classifiers along the path from the root to the leaf nodes of these dichotomies. Then, we formulate an optimization program to generate perturbations fooling NDCs and propose an algorithmic solution based on a convex relaxation. A solution is obtained by developing an ADMM-based solver to the convex programs. The experiments show that NDCs are more robust than their single stage counterpart in that the optimal perturbations inducing misclassifications are more perceptible.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114500624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Learning Parametric Time-Vertex Graph Processes from Incomplete Realizations 从不完全实现中学习参数化时间顶点图过程
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596563
Eylem Tugçe Güneyi, Abdullah Canbolat, Elif Vural
{"title":"Learning Parametric Time-Vertex Graph Processes from Incomplete Realizations","authors":"Eylem Tugçe Güneyi, Abdullah Canbolat, Elif Vural","doi":"10.1109/mlsp52302.2021.9596563","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596563","url":null,"abstract":"We consider the problem of estimating time-varying graph signals with missing observations, which is of interest in many applications involving data acquisition on irregular topologies. We model time-varying graph signals as jointly stationary time-vertex ARMA graph processes. We formulate the learning of ARMA process parameters as an optimization problem where the joint power spectral density of the model is fit to a rough empirical estimate of the process covariance matrix. We propose a convex relaxation of this problem, which results in an algorithm more flexible than existing methods regarding the pattern of available and missing observations of the process. Experimental results on meteorological signals show that the proposed method compares favorably to reference state-of-the-art algorithms.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126032666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Early Fusion Graph Convolutional Network for Skeleton-Based Action Recognition 基于骨架动作识别的早期融合图卷积网络
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596448
Xiaoxue Zhao, Cuiwei Liu, Xiangbin Shi
{"title":"Early Fusion Graph Convolutional Network for Skeleton-Based Action Recognition","authors":"Xiaoxue Zhao, Cuiwei Liu, Xiangbin Shi","doi":"10.1109/mlsp52302.2021.9596448","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596448","url":null,"abstract":"Skeleton-based action recognition has attracted much attention in computer vision. Recently, Graph Convolutional Networks (GCNs) with multi-stream fusion strategies have obtained remarkable performance. Most of these models make decisions of action recognition by merging the prediction scores of multiple streams, while ignoring the complementary properties of different data streams for building representative features. In this paper, we propose a novel Early Fusion Graph Convolutional Network (EF-GCN), which fuses hidden features extracted from multiple skeleton data streams at different levels to enhance the discriminative power of features. Unlike the previous GCN-based models that train networks corresponding to different streams independently, all the subnetworks in the proposed EF-GCN are jointly learned in an end-to-end manner. Experiments conducted on two skeleton datasets (i.e., NTU-RGB+D and NTU-120 RGB+D) show the superior performance of EF-GCN.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122185933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信