{"title":"LJSing: Large-Scale Singing Voice Corpus of Single Japanese Singer","authors":"Takuto Fujimura, Takashi Nose, A. Ito","doi":"10.1109/GCCE50665.2020.9291704","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9291704","url":null,"abstract":"This paper describes the construction of the LJSing, a large-scale Japanese singing voice corpus by a single female singer for singing voice synthesis based on statistical methods. Singing voice synthesis systems based on machine learning have been widely studied. However, most Japanese singing voice corpora are not enough for the training of recent deep-learningbased synthesis. Furthermore, those corpora were designed without phonetic and prosodic balance. Therefore, we recorded and labeled a five-hour phonetically and prosodically balanced singing corpus sung by a Japanese singer. The corpus consists of two data sets, SongSet and PhraseSet, which are constructed based on songs and phrases, respectively.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"247 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115019396","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}
{"title":"Dam Water Overflow Estimation using Time Series","authors":"Mie Mie Khin, Mie Mie Tin, Thi Thi Zin, P. Tin","doi":"10.1109/GCCE50665.2020.9291993","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9291993","url":null,"abstract":"This paper will implement the water level estimation of the dam from Myanmar. We use the time series stochastic model to calculate the water level estimation varying on in flow and consumption of dam. This approach is applying probability of Markovian Time Series. This paper based on rainfall and the other factors of dam water storage such as inflow and outflow of dam. This result estimate actual monthly water spread area and shows error is small. This research result also highlight that Markovian Time Series model is one of the best estimate processes for water level estimation.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115091905","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}
{"title":"Data Model for Registered Tangible Cultural Properties Using Linked Data","authors":"Shinya Oguri, Mayu Urata, M. Endo, T. Yasuda","doi":"10.1109/gcce50665.2020.9291783","DOIUrl":"https://doi.org/10.1109/gcce50665.2020.9291783","url":null,"abstract":"National registered tangible cultural properties complement important cultural properties and are widely protected under less strict regulations. In recent years, it is expected that cultural properties will be used for local tourism and town planning. In this case, an effective cultural property database is required. However, the current database of nationally designated cultural properties is mainly for the purpose of preserving cultural properties, and there are problems such as overlapping names and addresses. Therefore, it is not an effective means for utilizing cultural properties. In this study, we propose a method to describe the information of a registered tangible cultural property building to improve the convenience of its use. In the construction, cooperation data was carried out by utilizing Infrastructure for Multilayer Interoperability (IMI) Common Vocabulary. We applied the information of the national cultural properties database to the data model, and examined its applicability. As a result, this method solved the problem of overlapping the names and addresses of cultural properties. In addition, the possibility of utilizing cultural property buildings expanded by making the data structure into linked data.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115552187","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}
{"title":"3.7GHz Band Planar Antenna for 5th Generation Mobile Communication System","authors":"Koichi Karasawa, Tomoya Kusama, Akihiro Komiyama, Kazuki Ashida, Takahisa Karakama, Tutomu Kaneko","doi":"10.1109/GCCE50665.2020.9291870","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9291870","url":null,"abstract":"The 3. 7GHz band planar antenna for the 5th generation mobile communication system (5G) was proposed and examined. The 3. 7GHz band is 0. 5GHz frequency band from 3. 6GHz to 4.1GHz and very wide. In this study, a single planar antenna for the 3. 7GHz band is realized with the revised rake antenna. The practical maximum and the average gains are shown in the characteristics of the return loss and the radiation patterns.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122701848","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}
Tsanming Ou, Yuko Hoshino, Haruka Ohsuga, M. Yamada, T. Miyamoto
{"title":"The Humanoid Robot/Camera System for Teaching YOGA Exercise Motions","authors":"Tsanming Ou, Yuko Hoshino, Haruka Ohsuga, M. Yamada, T. Miyamoto","doi":"10.1109/GCCE50665.2020.9292075","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9292075","url":null,"abstract":"To address the problem of the shortage in caregivers, we have developed a system that can teach learners exercises with a humanoid robot. The system uses a depth camera and a humanoid robot. Here, we present the method we used to obtain the motion data when a learner imitates the exercise motions performed by the robot, and we examine the usefulness of the exercise instruction by the robot.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"244 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122499764","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}
{"title":"An Open-Source Web API implementation for ECHONET Lite","authors":"Marios Sioutis, Yasuo Tan","doi":"10.1109/GCCE50665.2020.9292076","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9292076","url":null,"abstract":"In this paper we discuss our development efforts towards a novel, open-source implementation of the Web API guidelines of ECHONET Lite. Currently a work in progress, we demonstrate the use of the full communication paths in the case of a device property or an echoCommand request, a path that is a representative example of using this ECHONET Lite Web service. The implementation consists of two entities, a web service written in Rust, and a home controller written in Java. The two entities communicate using a text-based, line-oriented protocol. The implementation is examined in terms of time overhead, its ability to parallelize workloads and its memory footprint. Experiment results show promising performance (200ms time overhead), ability to parallelize workloads and reasonable memory footprint.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116821201","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}
Kouki Ogata, Kazuma Takemoto, Takeshi Mizuguchi, Hiroki Yokoyama, A. A. Moe, Geunho Lee
{"title":"Shape-Variation Crawler Mechanism with Four Foldable Legs for Constant Platform Posture","authors":"Kouki Ogata, Kazuma Takemoto, Takeshi Mizuguchi, Hiroki Yokoyama, A. A. Moe, Geunho Lee","doi":"10.1109/GCCE50665.2020.9291858","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9291858","url":null,"abstract":"This paper practically tackles the design and implementation issue of maintaining a desired platform posture. As a solution approach, a novel shape-variation crawler mechanism is proposed, enabling a crawler robot to keep its desired posture while moving. More practically, the shape-variation crawler mechanism is implemented by employing individual foldable legs controlled by a toothed rack and pinion gear. The proposed crawler mechanism enables the robot to change its crawler shape according to a local surface topology. This paper details on the realization of the proposed mechanism. The effectiveness for the mechanism is evaluated through experiments after its realization.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116871873","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}
{"title":"Rate Adaptive P2P Stream Merging for Hybrid Sensor Data Recovery","authors":"Ei Khaing Win, T. Yoshihisa","doi":"10.1109/GCCE50665.2020.9292021","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9292021","url":null,"abstract":"In IoT data recovery such as video data recovery or sensor data recovery, stream merging plays an important role to reduce the bandwidth consumption. In the existing peer-to-peer recovery scheme, to maintain the static nature of quality expectation, past data delivery rate adaptability is not considered in stream merging. However, depending on any form of emergency or issues, there are cases in which the loss-encountered client accepts the quality changes at its recovery time. Hence, we introduce a rate adaptive peer-to-peer stream merging (RAPSM) for hybrid sensor data recovery scheme. From our simulation results, we confirmed that our proposed method reduces more of the number of recovery streams.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124765971","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}
Yuichi Mashiba, H. E. B. Salih, N. Wakatsuki, K. Mizutani, K. Zempo
{"title":"QR Code Without Impairing the Scenery and Detection System for the visually impaired","authors":"Yuichi Mashiba, H. E. B. Salih, N. Wakatsuki, K. Mizutani, K. Zempo","doi":"10.1109/GCCE50665.2020.9291733","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9291733","url":null,"abstract":"We proposed QR code without impairing the scenery and detection system for the visually impaired. This system enables visually impaired people to receive information using invisible QR code and IR camera. We verified the invisibility of QR codes made of combining infrared absorbing ink and reflective ink, and to compare them with existing visible QR codes. The invisible QR code was read by an IR camera, both the readable distance and angle decreased. Proposed system was compared with the information acquisition using the tactile sense, and the usefulness was confirmed experimentally. At the same time, system usability was evaluated. It was confirmed that the information could be obtained more quickly than the tactile information and the evaluation from the visually impaired was higher than average.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123993671","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}
Weihao Zhuang, T. Hascoet, R. Takashima, T. Takiguchi, Y. Ariki
{"title":"Convolutional neural networks Memory optimization Inference with Splitting Image","authors":"Weihao Zhuang, T. Hascoet, R. Takashima, T. Takiguchi, Y. Ariki","doi":"10.1109/GCCE50665.2020.9291891","DOIUrl":"https://doi.org/10.1109/GCCE50665.2020.9291891","url":null,"abstract":"In this paper, we propose a method to reduce the memory requirement of Convolutional Neural Networks (CNN) in the inference phase. Before feeding an input image into the CNN model, input image will split evenly to several sub-images and feed them into models respectively and combine the output after a certain layer.","PeriodicalId":179456,"journal":{"name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114351488","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}