Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848518
S. Phaiboon, Khunchai Tanukitwattana
This paper presents electrical energy predicting from sea waves in Thailand using fuzzy logic approximation. We installed a study of 300 W electric generator and performed measurement of the wave height and electric power generating. This information is used for modeling to analyze the relationship Then we applied our fuzzy model to predict the electric generation from sea wave in Gulf of Thailand and Andaman sea. The results show comfortable and fast predicting with high accuracy for uncertain sea wave energy.
{"title":"Fuzzy model for predicting electric generation from sea wave energy in Thailand","authors":"S. Phaiboon, Khunchai Tanukitwattana","doi":"10.1109/TENCON.2016.7848518","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848518","url":null,"abstract":"This paper presents electrical energy predicting from sea waves in Thailand using fuzzy logic approximation. We installed a study of 300 W electric generator and performed measurement of the wave height and electric power generating. This information is used for modeling to analyze the relationship Then we applied our fuzzy model to predict the electric generation from sea wave in Gulf of Thailand and Andaman sea. The results show comfortable and fast predicting with high accuracy for uncertain sea wave energy.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114382228","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848735
N. Radzi, M. A. Ridwan, F. Abdullah, N. M. Din, M. Al-Mansoori, H. Z. Abidin
Passive Optical Network (PON) testbed has been the interests of many researchers nowadays to study the non-linear effects of fibers that could not be captured using simulations. The length of the fiber is significant because cost savings could be made with longer fiber by reducing the electronic equipment and real-estate required at the local exchange or wire center. In this paper, we vary the fiber length ranges from 5 km, 10 km, 15 km and 20 km to study the effects they produce towards the packet delay. The experiment is done in a Peripheral Interface Controller (PIC) based PON testbed, and validated by National Instrument - Universal Software Radio Peripheral (NI-USRP) based PON testbed. The results show that the percentage difference between each fiber length is very minor, where we can observe as high as 0.12% between 10 km to 5 km fiber length, 0.65% between 15 km to 10 km fiber length, 0.3% between 20 km to 10 km fiber length and only 1.1% between 20 km to 5 km fiber length.
{"title":"Effects of varying fiber length towards packet delay in Passive Optical Network","authors":"N. Radzi, M. A. Ridwan, F. Abdullah, N. M. Din, M. Al-Mansoori, H. Z. Abidin","doi":"10.1109/TENCON.2016.7848735","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848735","url":null,"abstract":"Passive Optical Network (PON) testbed has been the interests of many researchers nowadays to study the non-linear effects of fibers that could not be captured using simulations. The length of the fiber is significant because cost savings could be made with longer fiber by reducing the electronic equipment and real-estate required at the local exchange or wire center. In this paper, we vary the fiber length ranges from 5 km, 10 km, 15 km and 20 km to study the effects they produce towards the packet delay. The experiment is done in a Peripheral Interface Controller (PIC) based PON testbed, and validated by National Instrument - Universal Software Radio Peripheral (NI-USRP) based PON testbed. The results show that the percentage difference between each fiber length is very minor, where we can observe as high as 0.12% between 10 km to 5 km fiber length, 0.65% between 15 km to 10 km fiber length, 0.3% between 20 km to 10 km fiber length and only 1.1% between 20 km to 5 km fiber length.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114383836","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848740
K. Low, M. Tissera, J. W. Chia
VELOX-II is among the first few 6U nano-satellites in the world that have been successfully launched and operated in space. The satellite was developed and built in the Satellite Research Centre (SaRC) at Nanyang Technological University (NTU). It is SaRC's sixth satellite in orbit. It carries a communication payload to demonstrate inter-satellite data relay system capability between a low earth orbit (LEO) and higher orbit satellites. Its primary aim is to demonstrate data transmission anytime and anywhere in the orbit. Besides the primary communication payload, the satellite missions include a GPS payload for precise orbit navigation and a fault tolerant electronic circuit. In this paper, the missions of VELOX-II are described and in-orbit flight results are presented.
{"title":"In-orbit results of VELOX-II nanosatellite","authors":"K. Low, M. Tissera, J. W. Chia","doi":"10.1109/TENCON.2016.7848740","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848740","url":null,"abstract":"VELOX-II is among the first few 6U nano-satellites in the world that have been successfully launched and operated in space. The satellite was developed and built in the Satellite Research Centre (SaRC) at Nanyang Technological University (NTU). It is SaRC's sixth satellite in orbit. It carries a communication payload to demonstrate inter-satellite data relay system capability between a low earth orbit (LEO) and higher orbit satellites. Its primary aim is to demonstrate data transmission anytime and anywhere in the orbit. Besides the primary communication payload, the satellite missions include a GPS payload for precise orbit navigation and a fault tolerant electronic circuit. In this paper, the missions of VELOX-II are described and in-orbit flight results are presented.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114395745","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7847967
D. Rawat, B. B. Bista, Gongjun Yan
Data falsification attack is one of the main security issues in vehicular ad-hoc networks (VANETs) where vehicles rely on information received from other peers/vehicles. In this paper, we propose a method to detect data falsification attack using hash chains for enhancing the network performance by adapting contention window size to forward accurate information to the neighboring vehicles in a timely manner (to improve throughput while reducing end-to-end delay). Performance of the proposed approach is evaluated using numerical results obtained from simulations. We found that the proposed adaptive approach prevents VANET from data falsification attacks and provides higher throughput with lower delay.
{"title":"Securing vehicular ad-hoc networks from data falsification attacks","authors":"D. Rawat, B. B. Bista, Gongjun Yan","doi":"10.1109/TENCON.2016.7847967","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7847967","url":null,"abstract":"Data falsification attack is one of the main security issues in vehicular ad-hoc networks (VANETs) where vehicles rely on information received from other peers/vehicles. In this paper, we propose a method to detect data falsification attack using hash chains for enhancing the network performance by adapting contention window size to forward accurate information to the neighboring vehicles in a timely manner (to improve throughput while reducing end-to-end delay). Performance of the proposed approach is evaluated using numerical results obtained from simulations. We found that the proposed adaptive approach prevents VANET from data falsification attacks and provides higher throughput with lower delay.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114514514","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848700
Z. Jiang, Ken Shinohara
This paper addresses the issue of end-effector trajectory tracking control of multi-link flexible joint robot manipulators. A submanifold is designed to describe the ideal trajectory tracking performance. Dynamics of the robot is rewritten in terms of the manifold. Control schemes are derived using backstepping control design approach. Stability of the system is analyzed based on Lyapunov stability theory. Simulations are carried out to on a 2-link flexible robot manipulator. The results demonstrate effectiveness and usefulness of the proposed control method.
{"title":"Workspace trajectory tracking control of flexible joint robots based on backstepping method","authors":"Z. Jiang, Ken Shinohara","doi":"10.1109/TENCON.2016.7848700","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848700","url":null,"abstract":"This paper addresses the issue of end-effector trajectory tracking control of multi-link flexible joint robot manipulators. A submanifold is designed to describe the ideal trajectory tracking performance. Dynamics of the robot is rewritten in terms of the manifold. Control schemes are derived using backstepping control design approach. Stability of the system is analyzed based on Lyapunov stability theory. Simulations are carried out to on a 2-link flexible robot manipulator. The results demonstrate effectiveness and usefulness of the proposed control method.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117105123","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7847953
Zhuoran Xu, Cuiqin Hou, Yingju Xia, Jun Sun, Hiroya Inakoshi, N. Yugami
Data stream mining has gained growing attentions recently. Concept drift is a particular problem in data stream mining, which is defined as the distribution of data may change over time. Most of current methods try to estimate the current distribution or reconstruct the current distribution from a mixture of old distributions. They suffer problems of estimation and reconstruction error respectively. In this paper, we found that a classifier that fits the current distribution can be obtained more directly than the current methods by ensembling classifiers trained with increasing number of recent data. This strategy guarantees that no matter when and how concept drift happens, there is always a classifier that suits the current data distribution. So our method only needs to select the current distribution classifier out of all classifiers we hold. This is much easier than estimation and reconstruction. We test our method on four real world data sets. Comparing with other methods, our method is the best algorithm in terms of average accuracy.
{"title":"Pyramid stack data stream mining for handling concept-drifting","authors":"Zhuoran Xu, Cuiqin Hou, Yingju Xia, Jun Sun, Hiroya Inakoshi, N. Yugami","doi":"10.1109/TENCON.2016.7847953","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7847953","url":null,"abstract":"Data stream mining has gained growing attentions recently. Concept drift is a particular problem in data stream mining, which is defined as the distribution of data may change over time. Most of current methods try to estimate the current distribution or reconstruct the current distribution from a mixture of old distributions. They suffer problems of estimation and reconstruction error respectively. In this paper, we found that a classifier that fits the current distribution can be obtained more directly than the current methods by ensembling classifiers trained with increasing number of recent data. This strategy guarantees that no matter when and how concept drift happens, there is always a classifier that suits the current data distribution. So our method only needs to select the current distribution classifier out of all classifiers we hold. This is much easier than estimation and reconstruction. We test our method on four real world data sets. Comparing with other methods, our method is the best algorithm in terms of average accuracy.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129922086","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848103
Ying Sun, Wen-Tai Li, Wentu Song, C. Yuen
This paper stands an attacker's point of view to develop a novel attack strategy that causes as much destructive as possible to the topology of electric network. By attacking transmission lines, power flow of girds will be changed, which could cause overload on other lines and possibly trigger cascading failures, and then lead to large areas blackout. Meanwhile, considering the limited resource of attacker, we propose a method to find out the minimum value to corrupt the measurements of attacked area, in order to mislead the control centre into detecting wrong attacked locations. Finally, the proposed attack strategy is explained in detail by IEEE 9-bus systems, and extending this application to a more complex networks that verified by IEEE 14-bus systems. Simulation results show that the damage risks of electric grids, caused by the proposed strategy, are increased at least 50% compared with traditional attack strategy.
{"title":"Joint cyber and physical attacks against topology of electric grids","authors":"Ying Sun, Wen-Tai Li, Wentu Song, C. Yuen","doi":"10.1109/TENCON.2016.7848103","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848103","url":null,"abstract":"This paper stands an attacker's point of view to develop a novel attack strategy that causes as much destructive as possible to the topology of electric network. By attacking transmission lines, power flow of girds will be changed, which could cause overload on other lines and possibly trigger cascading failures, and then lead to large areas blackout. Meanwhile, considering the limited resource of attacker, we propose a method to find out the minimum value to corrupt the measurements of attacked area, in order to mislead the control centre into detecting wrong attacked locations. Finally, the proposed attack strategy is explained in detail by IEEE 9-bus systems, and extending this application to a more complex networks that verified by IEEE 14-bus systems. Simulation results show that the damage risks of electric grids, caused by the proposed strategy, are increased at least 50% compared with traditional attack strategy.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130483504","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848129
M. Chheng, A. Nerves
The study develops a fast and simple technique for on-line transient stability assessment for the case of fault disturbances in the power transmission system. A case study for stability preventive control by generation rescheduling illustrates an application of the proposed procedure. The study focuses on an implementation of an on-line contingency screening method. A regression model is built between the proposed stability index and the critical clearing time. This regression model is based on off-line calculations for application in real-time transient stability assessment. Three different stability indices are proposed: rotor Angle Increment index, Absolute Angle Increment index, and Kinetic Energy index. In the off-line computation, the regression model relationship between the chosen index and the critical clearing time is built. For on-line application, the critical clearing time is determined using the regression equation and the calculated stability index value. The IEEE 39-bus 10-machine test system is used to evaluate the performance of the proposed method.
{"title":"A regression model-based approach to fast contingency screening for transient stability","authors":"M. Chheng, A. Nerves","doi":"10.1109/TENCON.2016.7848129","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848129","url":null,"abstract":"The study develops a fast and simple technique for on-line transient stability assessment for the case of fault disturbances in the power transmission system. A case study for stability preventive control by generation rescheduling illustrates an application of the proposed procedure. The study focuses on an implementation of an on-line contingency screening method. A regression model is built between the proposed stability index and the critical clearing time. This regression model is based on off-line calculations for application in real-time transient stability assessment. Three different stability indices are proposed: rotor Angle Increment index, Absolute Angle Increment index, and Kinetic Energy index. In the off-line computation, the regression model relationship between the chosen index and the critical clearing time is built. For on-line application, the critical clearing time is determined using the regression equation and the calculated stability index value. The IEEE 39-bus 10-machine test system is used to evaluate the performance of the proposed method.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130512535","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848208
Santhakumar R, Megha Tandur, E. R. Rajkumar, G. S, Girish Haritz, K. Rajamani
Diabetic retinopathy is the most general diabetes complication that affects eyes and results in blindness. It's due to impairment of the arteries a veins located in the fundus of eye (retina) that are composed of light sensitive tissues. The aim of this research work is to design an efficient and sensitive tool for Diabetic Retinopathy using the images acquired from portable fundus camera. The screening tool is based on advanced machine learning and computer vision algorithm which includes patch level prediction. In patch level prediction algorithm will localize the diseased region in the Diabetic Retinopathy image like Hard Exudates and Hemorrhage. The patch level classification uses Support Vector Machine (SVM) machine learning classifier model to predict the potential patch of Hard Exudates and Hemorrhage. In this algorithm, the image is broken into regular rectangular patch. The feature for each patch along with the different class label based on the ground truth is computed and passed to strong classifier SVM. The data sets are split into training dataset and testing dataset. The classifier model is built on training dataset and tested against the test dataset. The performance results of rectangular patch level prediction using SVM the average performance for Hard Exudates was Accuracy 96 %, Sensitivity 94%, Specificity 96%. The average performance for Hemorrhage was Accuracy 85 %, Sensitivity 77%, and Specificity 85%.
{"title":"Machine learning algorithm for retinal image analysis","authors":"Santhakumar R, Megha Tandur, E. R. Rajkumar, G. S, Girish Haritz, K. Rajamani","doi":"10.1109/TENCON.2016.7848208","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848208","url":null,"abstract":"Diabetic retinopathy is the most general diabetes complication that affects eyes and results in blindness. It's due to impairment of the arteries a veins located in the fundus of eye (retina) that are composed of light sensitive tissues. The aim of this research work is to design an efficient and sensitive tool for Diabetic Retinopathy using the images acquired from portable fundus camera. The screening tool is based on advanced machine learning and computer vision algorithm which includes patch level prediction. In patch level prediction algorithm will localize the diseased region in the Diabetic Retinopathy image like Hard Exudates and Hemorrhage. The patch level classification uses Support Vector Machine (SVM) machine learning classifier model to predict the potential patch of Hard Exudates and Hemorrhage. In this algorithm, the image is broken into regular rectangular patch. The feature for each patch along with the different class label based on the ground truth is computed and passed to strong classifier SVM. The data sets are split into training dataset and testing dataset. The classifier model is built on training dataset and tested against the test dataset. The performance results of rectangular patch level prediction using SVM the average performance for Hard Exudates was Accuracy 96 %, Sensitivity 94%, Specificity 96%. The average performance for Hemorrhage was Accuracy 85 %, Sensitivity 77%, and Specificity 85%.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123849695","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}
Pub Date : 2016-11-01DOI: 10.1109/TENCON.2016.7848421
Sanket Barhate, S. Kshirsagar, Niramay Sanghvi, Kamini Sabu, P. Rao, N. Bondale
Text-to-speech synthesizers present an attractive alternative to reading in hands-free communication scenarios. Speech intelligibility and naturalness are key to the user acceptability of synthesized speech. The accurate modeling of prosody plays an important role in both dimensions. While prosody is language dependent, it is also strongly dependent on the speaking style. In this work, we study the important prosodic features of news reading style in Marathi using publicly available radio broadcasts. Prominence and boundaries are among the important linguistic cues conveyed via a news reader's prosody. Using perception testing, we obtain boundaries and prominent words in broadcast recordings of two female news readers. We measure acoustic parameters known to serve as cues to prominence such as the fundamental frequency, duration and intensity. We also make observations on timing and pitch phenomena at inter- and intra-sentence breaks. Our results indicate that prominence depends strongly on achieved FO span in the word and to a smaller extent on duration increase. Breaks are signaled by pauses and pre-boundary lengthening of the final syllable. We observe that, unlike English, sentence ending in Marathi is not always accompanied by a pitch fall in the final syllable. The implications of these observations on prosody generation are discussed.
{"title":"Prosodic features of Marathi news reading style","authors":"Sanket Barhate, S. Kshirsagar, Niramay Sanghvi, Kamini Sabu, P. Rao, N. Bondale","doi":"10.1109/TENCON.2016.7848421","DOIUrl":"https://doi.org/10.1109/TENCON.2016.7848421","url":null,"abstract":"Text-to-speech synthesizers present an attractive alternative to reading in hands-free communication scenarios. Speech intelligibility and naturalness are key to the user acceptability of synthesized speech. The accurate modeling of prosody plays an important role in both dimensions. While prosody is language dependent, it is also strongly dependent on the speaking style. In this work, we study the important prosodic features of news reading style in Marathi using publicly available radio broadcasts. Prominence and boundaries are among the important linguistic cues conveyed via a news reader's prosody. Using perception testing, we obtain boundaries and prominent words in broadcast recordings of two female news readers. We measure acoustic parameters known to serve as cues to prominence such as the fundamental frequency, duration and intensity. We also make observations on timing and pitch phenomena at inter- and intra-sentence breaks. Our results indicate that prominence depends strongly on achieved FO span in the word and to a smaller extent on duration increase. Breaks are signaled by pauses and pre-boundary lengthening of the final syllable. We observe that, unlike English, sentence ending in Marathi is not always accompanied by a pitch fall in the final syllable. The implications of these observations on prosody generation are discussed.","PeriodicalId":246458,"journal":{"name":"2016 IEEE Region 10 Conference (TENCON)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121213546","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：