2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)最新文献_第8页

An Improved Retinex low-illumination image enhancement algorithm 一种改进的Retinex低照度图像增强算法

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023017

Shao-Chuan Wang, D. Gao, Yangping Wang, Song Wang

{"title":"An Improved Retinex low-illumination image enhancement algorithm","authors":"Shao-Chuan Wang, D. Gao, Yangping Wang, Song Wang","doi":"10.1109/APSIPAASC47483.2019.9023017","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023017","url":null,"abstract":"Low-illumination images are generally low-quality images. The retinex algorithm can cause halo artifacts and loss of details in processing. Therefore, an improved Retinex algorithm is proposed. Firstly, the HSI color space which is more in line with the human visual characteristics is selected instead of the RGB image, that is, the luminance component I is processed. Then, the illuminance image is estimated by using a guided filter that fuses the edge detection operator, and the edge detection operator can be better positioned. At the edge, an illuminance image with rich edge information can be obtained; after obtaining the illuminance image, the reflected image can be obtained by the Retinex principle, the obtained reflected image is subjected to low-rank decomposition, and the low-rank property of the image is used to suppress the enlarged halo and the enhancement process. Noise; finally, the visual effect is further improved by local contrast enhancement. Experiments show that the algorithm can effectively improve the brightness and contrast of the image, preserve the details of the image, and also suppress the noise interference in the enhancement process. The subjective visual effect and objective evaluation results of the image have also been greatly improved.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133853842","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 DOA Estimation Method in the presence of unknown mutual coupling based on Nested Arrays 基于嵌套数组的未知互耦DOA估计方法

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023028

Julan Xie, Fanghao Cheng, Zishu He, Huiyong Li

{"title":"A DOA Estimation Method in the presence of unknown mutual coupling based on Nested Arrays","authors":"Julan Xie, Fanghao Cheng, Zishu He, Huiyong Li","doi":"10.1109/APSIPAASC47483.2019.9023028","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023028","url":null,"abstract":"A novel DOA method is proposed to deal with the DOA estimation in the presence of the unknown mutual coupling for nested arrays. By using a new expression of the steering matrix in the presence of mutual coupling, a novel expression of the receiving data vector in the virtual array field is available. Then, based on a modified direction matrix constructed with block matrix, which relates to space discretized sampling grid, the sparse Bayesian compressive sensing method applies to estimate a vector, which contains the signal powers information and the mutual coupling information. The problem of off-grid DOAs is also considered for sparse Bayesian compressive sensing. Based on the estimated vector, a peak searching is performed to estimate the initial DOA. Finally, the estimation of DOA is modified to initial estimate plus off-grid error value. The advantage of fully utilizing the degree of freedom of nested arrays is preserved in this proposed algorithm. Moreover, no complicated calculation is needed to obtain the mutual coupling coefficients or rearrange the position of array element. Theoretical analysis and simulation results show the effectiveness of the proposed algorithm.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132901965","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

Robust Demixing Filter Update Algorithm Based on Microphone-wise Coordinate Descent for Independent Deeply Learned Matrix Analysis 基于麦克风坐标下降的独立深度学习矩阵分析鲁棒去混滤波器更新算法

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023032

Naoki Makishima, Norihiro Takamune, H. Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo

{"title":"Robust Demixing Filter Update Algorithm Based on Microphone-wise Coordinate Descent for Independent Deeply Learned Matrix Analysis","authors":"Naoki Makishima, Norihiro Takamune, H. Saruwatari, Daichi Kitamura, Yu Takahashi, Kazunobu Kondo","doi":"10.1109/APSIPAASC47483.2019.9023032","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023032","url":null,"abstract":"In this paper, we propose a robust demixing filter update algorithm for audio source separation, which is the task of recovering source signals from multichannel mixtures observed in a microphone array. Recently, independent deeply learned matrix analysis (IDLMA) has been proposed as a state-of-the-art separation method. IDLMA utilizes the deep neural network (DNN) inference of source models and the blind estimation of demixing filters based on sources' independence. In conventional IDLMA, iterative projection (IP) is exploited to estimate the demixing filters. Although IP is a fast algorithm, when a specific source model is not accurate owing to an unfavorable SNR condition, the subsequent update of filters will fail. This is because IP updates the demixing filters in a sourcewise manner, where only one source model is used for each update. In this paper, we derive a new microphone-wise update algorithm that exploits all information of the source models simultaneously for each update. The microphone-wise update problem cannot be solved by IP, but instead, a new type of vectorwise coordinate descent algorithm is introduced into the proposed algorithm to realize convergence-guaranteed parameter estimation. Experimental results show that the proposed update algorithm achieves better separation performance than IP.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116041385","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 Hue Correction Scheme Based on Constant-Hue Plane for Color Image Enhancement 一种基于恒色相平面的彩色图像增强色相校正方案

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023061

Yuma Kinoshita, Kouki Seo, H. Kiya

{"title":"A Hue Correction Scheme Based on Constant-Hue Plane for Color Image Enhancement","authors":"Yuma Kinoshita, Kouki Seo, H. Kiya","doi":"10.1109/APSIPAASC47483.2019.9023061","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023061","url":null,"abstract":"In this paper, we propose a novel hue correction scheme based on constant-hue plane in the RGB color space for color image enhancement. A number of hue-preserving image enhancement methods have already been proposed. Although these methods can preserve hue, these methods cannot be applied to the state-of-the-art enhancement methods such as deep-learning based ones. We therefore generalize a hue-preserving method based on the constant-hue plane in this paper. This generalization derives our novel hue correction scheme. In the proposed scheme, any existing image enhancement method including deep-learning based ones can be used to enhance images. The hue distortion due to the enhancement is then removed by replacing the maximally saturated colors of an enhanced image with those of the corresponding input one. Experimental results show that the proposed scheme is effective to suppress the hue distortion due to two color enhancement methods including a deep-learning based one. Furthermore, objective quality evaluations demonstrate that the proposed scheme can maintain the performance of image enhancement methods.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"79 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116466270","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

Automatic Ontology Population Using Deep Learning for Triple Extraction 基于深度学习的三重抽取本体自动填充

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023113

Ming-Hsiang Su, Chung-Hsien Wu, Po-Chen Shih

{"title":"Automatic Ontology Population Using Deep Learning for Triple Extraction","authors":"Ming-Hsiang Su, Chung-Hsien Wu, Po-Chen Shih","doi":"10.1109/APSIPAASC47483.2019.9023113","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023113","url":null,"abstract":"Ontology is a kind of representation used to represent knowledge in a form that computers can derive the content meaning. The purpose of this work is to automatically populate an ontology using deep neural networks for updating an ontology with new facts from an input knowledge resource. In this study for automatic ontology population, a bi-LSTM-based term extraction model based on character embedding is proposed to extract the terms from a sentence. The extracted terms are regarded as the concepts of the ontology. Then, a multi-layer perception network is employed to decide the predicates between the pairs of the extracted concepts. The two concepts (one serves as subject and the other as object) along with the predicate form a triple. The number of occurrences of the dependency relations between the concepts and the predicates are estimated. The predicates with low occurrence frequency are filtered out to obtain precise triples for ontology population. For evaluation of the proposed method, we collected 46,646 sentences from Ontonotes 5.0 for training and testing the bi-LSTM-based term extraction model. We also collected 404,951 triples from ConceptNet 5 for training and testing the multilayer perceptron-based triple extraction model. From the experimental results, the proposed method could extract the triples from the documents, achieving 74.59% accuracy for ontology population.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115260496","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: 5

Robust Camera Model Identification Based on Richer Convolutional Feature Network 基于更丰富卷积特征网络的鲁棒相机模型识别

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023334

Zeyu Zou, Yunxia Liu, Wen-Na Zhang, Yuehui Chen, Yun-Li Zang, Yang Yang, Bonnie Ngai-Fong Law

引用次数: 2

Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks 基于时间卷积递归神经网络的单通道语音增强

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023013

Jingdong Li, Hui Zhang, Xueliang Zhang, Changliang Li

{"title":"Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks","authors":"Jingdong Li, Hui Zhang, Xueliang Zhang, Changliang Li","doi":"10.1109/APSIPAASC47483.2019.9023013","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023013","url":null,"abstract":"In recent decades, neural network based methods have significantly improved the performance of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform using the estimated T-F representation. In this work, we proposed the temporal convolutional recurrent network (TCRN), an end-to-end model that directly map noisy waveform to clean waveform. The TCRN, which is combined convolution and recurrent neural network, is able to efficiently and effectively leverage short-term ang long-term information. Furthermore, we present the architecture that iterately downsample and upsample speech during forward propagation. We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks. Furthermore, We present several key techniques to stabilize the training process. The experimental results show that our model consistently outperforms existing speech enhancement approaches, in terms of speech intelligibility and quality.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"254 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114649487","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

Dilated-Gated Convolutional Neural Network with A New Loss Function on Sound Event Detection 基于新损失函数的扩展门控卷积神经网络在声音事件检测中的应用

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023308

Ke-Xin He, Weiqiang Zhang, Jia Liu, Yao Liu

引用次数: 1

Prosodic Realization of Focus in English by Bidialectal Mandarin Speakers 双语者英语焦点的韵律实现

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023060

Jiajing Zhang, Ying Chen, Jie Cui

引用次数: 1

SINGAN: Singing Voice Conversion with Generative Adversarial Networks 歌唱声音转换与生成对抗网络

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023162

Berrak Sisman, K. Vijayan, M. Dong, Haizhou Li

{"title":"SINGAN: Singing Voice Conversion with Generative Adversarial Networks","authors":"Berrak Sisman, K. Vijayan, M. Dong, Haizhou Li","doi":"10.1109/APSIPAASC47483.2019.9023162","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023162","url":null,"abstract":"Singing voice conversion (SVC) is a task to convert the source singer's voice to sound like that of the target singer, without changing the lyrical content. So far, most of the voice conversion studies mainly focus only on the speech voice conversion that is different from singing voice conversion. We note that singing conveys both lexical and emotional information through words and tones. It is one of the most expressive components in music and a means of entertainment as well as self expression. In this paper, we propose a novel singing voice conversion framework, that is based on Generative Adversarial Networks (GANs). The proposed GAN-based conversion framework, that we call SINGAN, consists of two neural networks: a discriminator to distinguish natural and converted singing voice, and a generator to deceive the discriminator. With GAN, we minimize the differences of the distributions between the original target parameters and the generated singing parameters. To our best knowledge, this is the first framework that uses generative adversarial networks for singing voice conversion. In experiments, we show that the proposed method effectively converts singing voices and outperforms the baseline approach.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122698943","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: 28