2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)最新文献_第5页

A Fabry-Perot interferometer demodulation method based on correlation detection 基于相关检测的法布里-珀罗干涉仪解调方法

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232051

Jun Hu, M. Fu

引用次数: 0

End-to-End Low-Resource Speech Recognition with a Deep CNN-LSTM Encoder 基于深度CNN-LSTM编码器的端到端低资源语音识别

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232119

Wen Wang, Xiaodong Yang, Hongwu Yang

{"title":"End-to-End Low-Resource Speech Recognition with a Deep CNN-LSTM Encoder","authors":"Wen Wang, Xiaodong Yang, Hongwu Yang","doi":"10.1109/ICICSP50920.2020.9232119","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232119","url":null,"abstract":"The performance of large vocabulary continuous automatic speech recognition (ASR) has improved tremendously due to the application of deep learning. However, building a low-resource ASR system remains a challenging task due to the difficulty of data collection and the lack of linguistic knowledge in the low-resource language. In this paper, we proposed an end-to-end low-resource speech recognition method and validated using the Tibetan language as an example. We firstly designed a Tibetan text corpus, and we also recorded a Tibetan speech corpus. Then, we extracted the spectrogram as a feature of each speech. The encoder is a single structure of the deep convolutional neural network (CNN) based on the VGG network and a hybrid network of deep CNN and long short-term memory (LSTM) network. The connectionist temporal classification (CTC) network sits on top of the encoder to infer the alignments between speech and label sequences. The experimental results show that the single structure encoder achieved a word error rate of 36.85%. The hybrid structure encoder achieves a 6% word error rate reduction compared to a single structure encoder. Also, when increasing the number of CNN layers in the encoder, the word error rate is further reduced.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128268589","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

An Improved Complex-valued FastICA Algorithm for Jamming Signals Sorting in Beidou Navigation Satellite System 一种改进的复值FastICA算法用于北斗卫星导航系统干扰信号的分选

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232049

Guangshun Xie, Huaiyu Tang, Rui Xue

{"title":"An Improved Complex-valued FastICA Algorithm for Jamming Signals Sorting in Beidou Navigation Satellite System","authors":"Guangshun Xie, Huaiyu Tang, Rui Xue","doi":"10.1109/ICICSP50920.2020.9232049","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232049","url":null,"abstract":"The minimum level of the signal received by receiving antennas is extremely weak in the Beidou navigation satellite system (BDS) due to distance attenuation. The jamming of different modulation types directly affects the performance of the navigation receiver or even prevent its normal operation. Sorting the jamming of different modulation types at the receiving end will help the anti-jamming design of the Beidou receiver, thereby improving the receiver’s anti-jamming performance. The complex-valued fast independent component analysis (FastICA) is unsuitable for sorting multiple jamming signals under the condition of low signal-to-noise ratio (SNR). Thus, this paper proposes an improved complex FastICA (c-FastICA) algorithm. First, the noise channel is introduced in the observation signals, and pseudo-whitening is performed. Then, the noise factor is introduced in the update iteration of the separation matrix to form a new iterative formula. Subsequently, the separation matrix is solved through Newton iteration. Finally, the separation matrix is multiplied by the preprocessed mixing matrix to obtain the separated signals. Theoretical analysis and simulation results show that compared with the denoising c-FastICA algorithm, the proposed algorithm greatly improves the separation effect in the case of low SNR and has a lower and more stable Amari index.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128559890","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

A Grouping Adaptive MIMO-OFDM Modulation Method for PLC PLC分组自适应MIMO-OFDM调制方法

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232039

Yingxue Li, Min Zhang, Xiao Zhang, Guocheng Li, Jun Lu

引用次数: 0

A Robust Residual Echo Suppression Algorithm Even During Double Talk 一种鲁棒的双通话残馀回波抑制算法

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232011

Bingxiao Fang

引用次数: 2

Numerical Study of Acoustic Propagation Characteristics in the Multi-scale Seafloor Random Media 多尺度海底随机介质中声传播特性的数值研究

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232061

Kaifeng Han, Wen Zhang, Chen Liu

引用次数: 0

A Time-domain Unsupervised Learning Based Sound Source Localization Method 基于时域无监督学习的声源定位方法

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232117

Yankun Huang, Xihong Wu, T. Qu

引用次数: 7

A robust traffic scene recognition algorithm based on deep learning and Markov localization 基于深度学习和马尔可夫定位的鲁棒交通场景识别算法

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232095

Guoan Yang, Zirui Zhao, Zhengzhi Lu, Junjie Yang, Deyang Liu, Yong Yang, Chuanbo Zhou

{"title":"A robust traffic scene recognition algorithm based on deep learning and Markov localization","authors":"Guoan Yang, Zirui Zhao, Zhengzhi Lu, Junjie Yang, Deyang Liu, Yong Yang, Chuanbo Zhou","doi":"10.1109/ICICSP50920.2020.9232095","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232095","url":null,"abstract":"This paper designs a traffic scene recognition module for the agent’s perception system. First, we enabled the output features of the convolutional neural network to be the descriptor of the traffic scene and adapted to the cost function of the image sequence to construct the observation module of the agent. Second, we assumed that the movement of the agent would be recursively updated and wouldn’t jump dramatically, which simultaneously possesses the Markov property, so the Markov localization algorithm was used to improve overall robustness. Third, the Kalman filter method was adopted to represent the probability distribution of the entire system using the first and second moments of the Gaussian distribution, so that the loop iteration in the state estimation can be transformed into a linear operation, and the penalty term in the standard variance of the observation probability can also be added to describe the reliability of the observation. Experimental results show that the agent can efficiently remove unreliable observations and achieve robust recognition accuracy of the traffic scene in all weather conditions.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":"333 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122845922","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

Speech Emotion Recognition based on Interactive Convolutional Neural Network 基于交互卷积神经网络的语音情感识别

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9232071

Huihui Cheng, Xiaoyu Tang

引用次数: 3

Correlation Filter-based Object Tracking Algorithms 基于相关滤波的目标跟踪算法

2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP) Pub Date : 2020-09-01 DOI: 10.1109/ICICSP50920.2020.9231974

Songke Zhao, Kewei Sun, Yuanfa Ji, Ning Guo, Xizi Jia

引用次数: 0