2020 15th IEEE International Conference on Signal Processing (ICSP)最新文献_第9页

Clustering SIFT: An Efficient Way to Achieve Flipping Invariance 聚类SIFT:实现翻转不变性的有效方法

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320908

Guoquan Li, Ruiyang Xia, Zhengwen Huang, Lingyun Wen, Huiqian Wang

引用次数: 0

Arbitrary Clutter PHD Filter and Its Implementation 任意杂波PHD滤波器及其实现

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320953

Xinglin Shen, Luping Zhang, Moufa Hu

引用次数: 1

Language Identification with Unsupervised Phoneme-like Sequence and TDNN-LSTM-RNN 无监督类音素序列与TDNN-LSTM-RNN语言识别

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320919

Linjia Sun

{"title":"Language Identification with Unsupervised Phoneme-like Sequence and TDNN-LSTM-RNN","authors":"Linjia Sun","doi":"10.1109/ICSP48669.2020.9320919","DOIUrl":"https://doi.org/10.1109/ICSP48669.2020.9320919","url":null,"abstract":"A novel language identification (LID) method is proposed that accepts the architecture of time delay neural network (TDNN) followed by long short term memory (LSTM) recurrent neural network (RNN) to learn long-term phonetic patterns and model the phonetic dynamics for different languages. Instead of the linguistic phonemes, the phoneme-like speech units are used to train the TDNN-LSTM-RNN, which can be found without prior linguistic knowledge and manual transcriptions. Compared with PPRLM, the experiment results show that the phoneme-like speech units by unsupervised discovering and the linguistic phonemes by manual annotation have the same effect in the LID task. Furtherly, the proposed LID method is built and reported the test results on the NIST LRE07 and the task of dialect identification. We compare the proposed LID method with other state-of-the-art methods, including the acoustic feature based LID methods and the phonetic feature based LID methods. The experimental results show that our method provides competitive performance with the existing methods in the LID task. In particular, our method helps to capture robust discriminative information for short duration language identification and high accuracy for dialect identification.","PeriodicalId":237073,"journal":{"name":"2020 15th IEEE International Conference on Signal Processing (ICSP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128810386","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

Optimization Method of Sparse Array Frequency and Steering Invariant Beamforming 稀疏阵列频率优化与定向不变波束形成方法

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9321015

Weichuan Yu, Peiyu He, Zili Xu, Ao Cui, Xuewei Shi, Jing Lei

引用次数: 0

Simulation of Dynamic Ship Radiated Noise Signal 船舶动态辐射噪声信号仿真

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320983

Yuan Zheng, Bin Jiang, Gang Yang

{"title":"Simulation of Dynamic Ship Radiated Noise Signal","authors":"Yuan Zheng, Bin Jiang, Gang Yang","doi":"10.1109/ICSP48669.2020.9320983","DOIUrl":"https://doi.org/10.1109/ICSP48669.2020.9320983","url":null,"abstract":"The total intensity and the spectral distribution of ship’s radiated noise signal changes dynamically as the ship navigates. Conventional static simulation methods are focused on exhibiting non-changing or fixed patterns of signal’s characteristics. For applications that require high-fidelity models, methods that can correctly simulate the above mentioned dynamic characteristics are preferred. In this paper, such a method is proposed and investigated. It is an enhancement of the static simulation method. Firstly, the resulting statically simulated intermediate signals are taken and divided into segments in the time domain. Secondly, for each segment and each frequency point of signal’s linear and continuous spectrum, the intensities are adjusted according to the acoustic transmission loss formula and then merged. Finally, the modulation process is conducted. The simulation experiment results show that the simulated noise signals can exhibit the dynamic characteristics of the navigating ship through the variation on total signal intensity and spectral distribution. Moreover, the simulated signals are also smooth, natural, and non-sectional in auditory sense.","PeriodicalId":237073,"journal":{"name":"2020 15th IEEE International Conference on Signal Processing (ICSP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122001650","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

Maximum Likelihood Optimization of Linear Frequency Modulated Signal Based on Particle Swarm 基于粒子群的线性调频信号的最大似然优化

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9321091

Xiaohui Yu, Xinbo Li, Yiran Shi, Xiaodong Sun, Shiqian Wang

引用次数: 0

Visual Images Memory Recall Based on ClassRBM and Free Energy Minimization 基于ClassRBM和自由能量最小化的视觉图像记忆召回

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320956

Yiren Liu, Yanjiang Wang, Limiao Deng, Mingyue Gao, Weifeng Liu

{"title":"Visual Images Memory Recall Based on ClassRBM and Free Energy Minimization","authors":"Yiren Liu, Yanjiang Wang, Limiao Deng, Mingyue Gao, Weifeng Liu","doi":"10.1109/ICSP48669.2020.9320956","DOIUrl":"https://doi.org/10.1109/ICSP48669.2020.9320956","url":null,"abstract":"Mounting evidence suggests that the brain works in a Bayesian way. Probabilistic inference models based on Bayesian theory have been widely applied in human memory modeling, such as search of associative memory (SAM) and retrieving effectively from memory (REM). However, these lines of memory models can only determine the class of the test images during memory recall. They fail to recall the test visual image, which is referred to as mental imagery in cognitive psychology. In order to address this issue, in this paper, we first propose a memory model based on classification RBM (ClassRBM), in which a three-layer neural network is constructed with 500-800-500 units. The input layer and output layer represent the visual sensory images and corresponding labels, respectively, while the hidden layer stores the encoded visual information. Then we apply free energy minimization principle to train the model, in which we assume that the storage and recall processes of memory in human brain involve free energy minimization. Finally, the learned visual images can be reconstructed by probabilistically sampling the visual units over the hidden units. Comprehensive experiments show that the proposed memory model is capable of recalling images studied and can be applied to the modeling of mental images in the mind.","PeriodicalId":237073,"journal":{"name":"2020 15th IEEE International Conference on Signal Processing (ICSP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130885103","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

Three-Dimensional Cooperative TDOA Location Method with Multi-UAV Based on Quantum Wind Driven Optimization 基于量子风驱动优化的多无人机三维协同TDOA定位方法

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9321087

Hongyuan Gao, Shihao Wang, Zhiwei Zhang

引用次数: 1

Background Initialization Based on Adaptive Online Low-rank Subspace Learning 基于自适应在线低秩子空间学习的背景初始化

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320960

Guang Han, Guanghao Zhang, Xi Cai

引用次数: 1

Detection of Railway Tunnel lining Based on Adaptive Background Learning 基于自适应背景学习的铁路隧道衬砌检测

2020 15th IEEE International Conference on Signal Processing (ICSP) Pub Date : 2020-12-06 DOI: 10.1109/ICSP48669.2020.9320937

Yuxin Liu, Enze Yang, Shuoyan Liu

引用次数: 3