2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)最新文献_第6页

A Prosodic Mandarin Text-to-Speech System Based on Tacotron 基于Tacotron的汉语韵律文转语音系统

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023283

Chuxiong Zhang, S. Zhang, Haibin Zhong

引用次数: 7

Infrared Pedestrian Detection with Converted Temperature Map 红外行人检测转换温度图

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023228

Yifan Zhao, Jingchun Cheng, Wei Zhou, Chunxi Zhang, Xiong Pan

{"title":"Infrared Pedestrian Detection with Converted Temperature Map","authors":"Yifan Zhao, Jingchun Cheng, Wei Zhou, Chunxi Zhang, Xiong Pan","doi":"10.1109/APSIPAASC47483.2019.9023228","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023228","url":null,"abstract":"Infrared pedestrian detection aims to detect persons in outdoor thermal images. It shows a unique advantage in dark environment or bad weather compared to daytime visible images (the RGB image). Most current methods treat infrared detection the same way as with visible images, e.g. regarding the infrared image as a special gray-scale visible image. In this paper, we tackle this problem with more emphasis on the underlying temperature information in infrared images. We build an image-temperature transformation formula based upon infrared image formation theory, which can convert infrared image into temperature map with the prior of pedestrian pixel-temperature value. The whole detection process follows a two-stage manner. In the first stage, we use a common detector which treats the infrared image as the gray-scale visible image to provide primary detection results and a pedestrian position prior (the highest-confidence pedestrian detection box in each image). In the second stage, we convert infrared images into corresponding temperature maps and train a temperature net for detection. The final results consist of both the primary detection and the temperature net outputs, detecting pedestrians with characteristics in both image and temperature domain. We show that the converted temperature image is less affected by environmental factors, and that its detector shows amazing complementary ability with the primary detector. We carry out extensive experiments and analysis on two public infrared datasets, the OTCBVS dataset and the FLIR dataset; and demonstrate the effectiveness of incorporating temperature maps.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"40 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114042196","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: 15

A Study on Low-resource Language Identification 低资源语言识别研究

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023075

Zhaodi Qi, Yong Ma, M. Gu

引用次数: 3

Audio Integrated Active Noise Control System with Auto Gain Controller 带有自动增益控制器的音频集成有源噪声控制系统

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023148

Kenta Iwai, T. Nishiura

{"title":"Audio Integrated Active Noise Control System with Auto Gain Controller","authors":"Kenta Iwai, T. Nishiura","doi":"10.1109/APSIPAASC47483.2019.9023148","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023148","url":null,"abstract":"This paper proposes an audio integrated active noise control (ANC) system with an auto gain controller. An ANC system is one of the techniques for reducing unwanted noise and used to reduce the factory noise, engine noise, and so forth. In general, the ANC system cannot completely reduce the unwanted noise due to its principle. To solve this problem, an audio integrated ANC (AIANC) system has been proposed. The AIANC system uses the additional audio signal to mask the residual noise called error signal. Also, the AIANC system can be used for telecommunication under noisy environment, in which the voice is treated as the audio signal of the AIANC system. However, in the conventional AIANC system, the power of the audio signal cannot be adjusted to that of the error signal and it causes that the audio signal is too larger or smaller than the error signal. To solve this problem, the AIANC with an auto gain controller is proposed. The proposed AIANC system has the auto gain controller to adjust the power of the audio signal and that of the error signal. Then, the audio signal is emitted with the same power as the error signal. Simulation results shows that the proposed AIANC system can reduce the unwanted noise and adjust the power of the audio signal to that of the error signal.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"220 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":"122706160","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 Loss With Mixed Penalty for Speech Enhancement Generative Adversarial Network 语音增强生成对抗网络的混合惩罚损失

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023273

Jie Cao, Yaofeng Zhou, Hong Yu, Xiaoxu Li, Dan Wang, Zhanyu Ma

引用次数: 0

Multiple-Operation Image Anti-Forensics with WGAN-GP Framework 基于WGAN-GP框架的多操作图像反取证

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023173

Jianyuan Wu, Zheng Wang, Hui Zeng, Xiangui Kang

引用次数: 6

Lightweight models for weather identification 用于天气识别的轻型模型

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023242

Congcong Wang, Pengyu Liu, Ke-bin Jia, Siwei Chen

{"title":"Lightweight models for weather identification","authors":"Congcong Wang, Pengyu Liu, Ke-bin Jia, Siwei Chen","doi":"10.1109/APSIPAASC47483.2019.9023242","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023242","url":null,"abstract":"At present, the recognition of weather phenomena mainly depends on the weather sensors and the weather radar. However, large-scale deployment of meteorological observation equipment for intensive weather monitoring is difficult because it is expensive and difficult to maintain. Moreover, convolutional neural networks (CNNs) can also be used to identify weather phenomena, but existing methods require high computing power of equipment, making it difficult to deploy in practice. Therefore, designing a lightweight model that can be deployed in a small device with weak computing power is crucial for intensive weather monitoring. In this paper, we study the shortcomings of some existing lightweight models. By comparing the disadvantages of these models, a new lightweight model is proposed. In addition, considering the number of existing weather datasets are too small to meet real monitoring needs, so we produced a dataset with a more complex variety of weather phenomena. Through the experiments, the proposed method can save more than 25 times memory usage with only 1.55% accuracy lost compared with the best CNNs method which achieves state-of-the-art performance among the other lightweight models.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"30 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":"121853485","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

Speech representation based on tensor factor analysis and its application to speaker recognition and language identification 基于张量因子分析的语音表示及其在说话人识别和语言识别中的应用

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023128

D. Saito, So Suzuki, N. Minematsu

引用次数: 0

Improving the Spectra Recovering of Bone-Conducted Speech via Structural SIMilarity Loss Function 利用结构相似度损失函数改进骨传导语音的频谱恢复

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023226

Changyan Zheng, Jibin Yang, Xiongwei Zhang, Meng Sun, Kun Yao

{"title":"Improving the Spectra Recovering of Bone-Conducted Speech via Structural SIMilarity Loss Function","authors":"Changyan Zheng, Jibin Yang, Xiongwei Zhang, Meng Sun, Kun Yao","doi":"10.1109/APSIPAASC47483.2019.9023226","DOIUrl":"https://doi.org/10.1109/APSIPAASC47483.2019.9023226","url":null,"abstract":"Bone-conducted (BC) speech is immune to background noise, but suffers from low speech quality due to the severe loss of high-frequency components. The key to BC speech enhancement is to restore the missing parts in the spectra. However, even with advanced deep neural networks (DNN), some of the recovered components still lack expected spectro-temproal structures. Mean Square Error loss function (MSE) is the typical choice for supervised DNN training, but it can only measure the distance of the spectro-temporal points and is not able to evaluate the similarity of structures. In this paper, Structural SIMilarity loss function (SSIM) originated from image quality assessment is proposed to train the spectral mapping model in BC speech enhancement, and to our best knowledge, it is the first time that SSIM is deployed in DNN- based speech signal processing tasks. Experimental results show that compared with MSE, SSIM can acquire better objective results and obtain spectra with spectro-temporal structures more similar to the target one. Some adjustments of hyper-parameters in SSIM are made due to the difference between natural image and magnitude spectrogram, and the optimal choice of them are suggested. In addition, the effects of three components in SSIM are analyzed individually, aiming to help further study on the applications of this loss function in other speech signal processing tasks.","PeriodicalId":145222,"journal":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"34 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132680010","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: 4

Question Mark Prediction By Bert 伯特的问号预测

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Pub Date : 2019-11-01 DOI: 10.1109/APSIPAASC47483.2019.9023090

Yunqi Cai, Dong Wang

引用次数: 9