Pub Date : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019180
Chandan Kumar, Shatrughna Kumar, A. K. Mal
In Mixed signal design, we replace the resistor with the switched capacitor. Elimination of resistors leads to very fast and accurate implementation. For realization of the switched capacitor, we need capacitors and switches. These switches are controlled by clocks. Here, clocks wouldn't overlap in active case, so we develop Non-Overlapping Clock (NOC). Here, we design NOC generator based on pass transistor application. For excellent realization of the switched capacitor, the power dissipation and phase noise of the NOC generator must be minimum. Simulation results suggest that proposed circuit is power and area efficient as compared to the conventional NOC circuits.
{"title":"An efficient two-phase NOC generator for low frequency applications","authors":"Chandan Kumar, Shatrughna Kumar, A. K. Mal","doi":"10.1109/ICACCCT.2014.7019180","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019180","url":null,"abstract":"In Mixed signal design, we replace the resistor with the switched capacitor. Elimination of resistors leads to very fast and accurate implementation. For realization of the switched capacitor, we need capacitors and switches. These switches are controlled by clocks. Here, clocks wouldn't overlap in active case, so we develop Non-Overlapping Clock (NOC). Here, we design NOC generator based on pass transistor application. For excellent realization of the switched capacitor, the power dissipation and phase noise of the NOC generator must be minimum. Simulation results suggest that proposed circuit is power and area efficient as compared to the conventional NOC circuits.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117020777","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019409
Ranjith Anbalagan, A. Julian
MANET (Mobile Ad hoc Network) being the centralized wireless network and due to the ease of deployment it has gained popularity very rapidly and has a wide acceptance in different areas. There is an increasing use of MANET technology in recent years where quick network establishment is required. Energy is the scarcest resource in MANET. Cluster based networks are used to reduce the energy consumption and also by means of controlled flooding using GPS (Global Positioning System). Significant amount of energy is consumed in GPS's operation. Completely GPS free as well as GPS scarce positioning systems for wireless, mobile and ad hoc had been proposed by many authors in recent years. LAR (Location Aided Routing) scheme1 uses GPS to find the expected region, in order to provide controlled flooding. The amount of energy consumed and control overhead increases with the increase in the number of advertisement messages transmitted. In HCBLR (Handover Count Based Location Aided Routing for Cluster Networks) the expected region is calculated based on the handover count value of the mobile node, which forwards the flooding messages only to the cluster heads that are in the expected region. Thus there is reduced energy consumption when compared to other location based protocols.
{"title":"Handover Count Based Location Aided Routing for Cluster Networks (HCBLR)","authors":"Ranjith Anbalagan, A. Julian","doi":"10.1109/ICACCCT.2014.7019409","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019409","url":null,"abstract":"MANET (Mobile Ad hoc Network) being the centralized wireless network and due to the ease of deployment it has gained popularity very rapidly and has a wide acceptance in different areas. There is an increasing use of MANET technology in recent years where quick network establishment is required. Energy is the scarcest resource in MANET. Cluster based networks are used to reduce the energy consumption and also by means of controlled flooding using GPS (Global Positioning System). Significant amount of energy is consumed in GPS's operation. Completely GPS free as well as GPS scarce positioning systems for wireless, mobile and ad hoc had been proposed by many authors in recent years. LAR (Location Aided Routing) scheme1 uses GPS to find the expected region, in order to provide controlled flooding. The amount of energy consumed and control overhead increases with the increase in the number of advertisement messages transmitted. In HCBLR (Handover Count Based Location Aided Routing for Cluster Networks) the expected region is calculated based on the handover count value of the mobile node, which forwards the flooding messages only to the cluster heads that are in the expected region. Thus there is reduced energy consumption when compared to other location based protocols.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117167645","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019345
G. Mahendran, R. Dhanasekaran, K. N. Narmadha Devi
Diabetic Retinopathy is an ocular systemic disease caused by complication of diabetes. It is a major cause of blindness in both middle and advanced age group. Earlier recognition of diabetic retinopathy shields understanding from visual impairment. The heading side effect of this difficulty seeing is the exudates. Exudates are the melted watery grasping solutes, proteins, cells, or cell garbage spilled from the harmed veins into near by tissues or on tissue surfaces in the retina. The spillage of these proteins or lipids causes vision misfortune to the patients. Distinguishing the exudates ahead of time can protect the diabetic patients from difficulty seeing. Ophthalmologists use widening system to identify the exudates. But it causes the irritation to the patients' eyes. This paper focuses on an automated method which detects the diabetic retinopathy through identifying exudates by Morphological process in colour fundus retinal images and then segregates the severity of the lesions. The severity level of the disease was achieved by Cascade Neural Network (CNN) classifier.
{"title":"Morphological process based segmentation for the detection of exudates from the retinal images of diabetic patients","authors":"G. Mahendran, R. Dhanasekaran, K. N. Narmadha Devi","doi":"10.1109/ICACCCT.2014.7019345","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019345","url":null,"abstract":"Diabetic Retinopathy is an ocular systemic disease caused by complication of diabetes. It is a major cause of blindness in both middle and advanced age group. Earlier recognition of diabetic retinopathy shields understanding from visual impairment. The heading side effect of this difficulty seeing is the exudates. Exudates are the melted watery grasping solutes, proteins, cells, or cell garbage spilled from the harmed veins into near by tissues or on tissue surfaces in the retina. The spillage of these proteins or lipids causes vision misfortune to the patients. Distinguishing the exudates ahead of time can protect the diabetic patients from difficulty seeing. Ophthalmologists use widening system to identify the exudates. But it causes the irritation to the patients' eyes. This paper focuses on an automated method which detects the diabetic retinopathy through identifying exudates by Morphological process in colour fundus retinal images and then segregates the severity of the lesions. The severity level of the disease was achieved by Cascade Neural Network (CNN) classifier.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115998185","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019388
Arjun Paramarthalingam, T. T. Mirnalinee, M. Tamilarasan
Shape descriptors are more powerful to discern objects present in the images. The present work is focused on simple contour based shape descriptor using centroid distance function and it works on closed contour objects. Object area normalization is performed to obtain `N' normalized contour points. The centroid distance feature extraction is performed on all normalized points. It forms simple 1-D feature vector of size `N'. For similarity matching correlation coefficient metric is used. This shape descriptor satisfies affine invariance property. The proposed idea is tested on MPEG-7 CE Shape-1 Part-B dataset images to validate its effectiveness. Experimental results shows that proposed compact centroid distance shape descriptor is more accurate than basic centroid distance shape descriptor and it saves space and time requirements at processing.
形状描述符在识别图像中存在的物体方面更强大。本文主要研究基于简单轮廓的形状描述子，该描述子使用质心距离函数，适用于封闭轮廓对象。对目标区域进行归一化，得到“N”个归一化轮廓点。对所有归一化点进行质心距离特征提取。它形成大小为' N'的简单的1-D特征向量。相似度匹配采用相关系数度量。这个形状描述符满足仿射不变性。在MPEG-7 CE Shape-1 Part-B数据集图像上进行了测试，验证了该方法的有效性。实验结果表明，所提出的紧致形心距离形状描述子比基本形心距离形状描述子精度更高，节省了处理时的空间和时间要求。
{"title":"Compact centroid distance shape descriptor based on object area normalization","authors":"Arjun Paramarthalingam, T. T. Mirnalinee, M. Tamilarasan","doi":"10.1109/ICACCCT.2014.7019388","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019388","url":null,"abstract":"Shape descriptors are more powerful to discern objects present in the images. The present work is focused on simple contour based shape descriptor using centroid distance function and it works on closed contour objects. Object area normalization is performed to obtain `N' normalized contour points. The centroid distance feature extraction is performed on all normalized points. It forms simple 1-D feature vector of size `N'. For similarity matching correlation coefficient metric is used. This shape descriptor satisfies affine invariance property. The proposed idea is tested on MPEG-7 CE Shape-1 Part-B dataset images to validate its effectiveness. Experimental results shows that proposed compact centroid distance shape descriptor is more accurate than basic centroid distance shape descriptor and it saves space and time requirements at processing.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116472390","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019248
Yashika Katyal, Suhas V. Alur, Shipra Dwivedi
In the modern day world, road accidents have become very common. They not only cause damage to property, but also keep at risk the lives of people travelling. Road safety is an issue of national concern, looking at its magnitude and the incidental negative impacts on the economy, public health, safety and the general welfare of the people. These road accidents may be due to many reasons like rash driving, drink and driving, inexperience, jumping signals, ignoring signboards. Since, road accidents is an important issue to be addressed, this paper will be concentrating on avoiding the road accidents by concentrating mainly on-Drunk driving or drowsiness and lane discipline. The paper has two parts. Firstly, lane detection using Hough Transform. Secondly, eye detection of driver for drowsiness detection. Thus, the main focus is on the fatigue of the driver and his maintenance of lane discipline.
{"title":"Safe driving by detecting lane discipline and driver drowsiness","authors":"Yashika Katyal, Suhas V. Alur, Shipra Dwivedi","doi":"10.1109/ICACCCT.2014.7019248","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019248","url":null,"abstract":"In the modern day world, road accidents have become very common. They not only cause damage to property, but also keep at risk the lives of people travelling. Road safety is an issue of national concern, looking at its magnitude and the incidental negative impacts on the economy, public health, safety and the general welfare of the people. These road accidents may be due to many reasons like rash driving, drink and driving, inexperience, jumping signals, ignoring signboards. Since, road accidents is an important issue to be addressed, this paper will be concentrating on avoiding the road accidents by concentrating mainly on-Drunk driving or drowsiness and lane discipline. The paper has two parts. Firstly, lane detection using Hough Transform. Secondly, eye detection of driver for drowsiness detection. Thus, the main focus is on the fatigue of the driver and his maintenance of lane discipline.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116487078","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019178
Shatrughna Kumar, Chandan Kumar, Milan Mazumdar, M. Mondal
In this paper, a tri band butterfly shaped Microstrip feed antenna for 3.852/5.773/8.341GHz application is presented here. The proposed microstrip-fed antenna forms operating frequencies by inserting one pair of slots on the ground plane with same lengths at a same distance from the center symmetrically. The size of the proposed antenna is 20×20 mm. The proposed antenna is simulated by ANSOFT designer var. 7 Software. In this antenna we use FR4 substrate with design specification dielectric constant (εr) of 4.4, thicknesses (h) of 1.6mm and its dielectric loss tangent is 0.02. Proposed antenna is useful for various wireless applications.
本文设计了一种适用于3.852/5.773/8.341GHz的三波段蝶形微带馈电天线。提出的微带馈电天线通过在离中心相同距离的地平面上对称地插入一对长度相同的槽来形成工作频率。建议天线的尺寸为20×20毫米。采用ANSOFT designer var. 7软件对该天线进行了仿真。本天线采用设计规范介电常数(εr)为4.4，厚度(h)为1.6mm，介质损耗正切为0.02的FR4衬底。该天线适用于各种无线应用。
{"title":"Single-feed slotted antenna for triband applications","authors":"Shatrughna Kumar, Chandan Kumar, Milan Mazumdar, M. Mondal","doi":"10.1109/ICACCCT.2014.7019178","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019178","url":null,"abstract":"In this paper, a tri band butterfly shaped Microstrip feed antenna for 3.852/5.773/8.341GHz application is presented here. The proposed microstrip-fed antenna forms operating frequencies by inserting one pair of slots on the ground plane with same lengths at a same distance from the center symmetrically. The size of the proposed antenna is 20×20 mm. The proposed antenna is simulated by ANSOFT designer var. 7 Software. In this antenna we use FR4 substrate with design specification dielectric constant (εr) of 4.4, thicknesses (h) of 1.6mm and its dielectric loss tangent is 0.02. Proposed antenna is useful for various wireless applications.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123522996","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019211
R. Selva Bharathi, R. Priyadharshni, S. Ramesh
Mobile agent is a vehicle equipped with powerful transceiver and battery which finds the shortest path to gather data from the sensors and finally transports the data to the sink. Here the major problem is to minimize the tour length of the mobile agent. Artificial Bee Colony is a very effective optimization technique for optimization problems. Since Crossover operators have better exploration property this operator are added to the ABC algorithm. In current swarm each crossover operator is applied to two randomly selected parents. Two off-springs are generated from crossover and worst parent is replaced by best off-spring, other parent remains same. ABC with real coded crossover operator applied to travelling salesman problem. The experimental result shows that proposed algorithm performs better than the Spanning tree covering algorithm in terms of efficiency and accuracy.
{"title":"Artificial Bee Colony algorithm to find optimum path for mobile agents in Wireless Sensor Networks","authors":"R. Selva Bharathi, R. Priyadharshni, S. Ramesh","doi":"10.1109/ICACCCT.2014.7019211","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019211","url":null,"abstract":"Mobile agent is a vehicle equipped with powerful transceiver and battery which finds the shortest path to gather data from the sensors and finally transports the data to the sink. Here the major problem is to minimize the tour length of the mobile agent. Artificial Bee Colony is a very effective optimization technique for optimization problems. Since Crossover operators have better exploration property this operator are added to the ABC algorithm. In current swarm each crossover operator is applied to two randomly selected parents. Two off-springs are generated from crossover and worst parent is replaced by best off-spring, other parent remains same. ABC with real coded crossover operator applied to travelling salesman problem. The experimental result shows that proposed algorithm performs better than the Spanning tree covering algorithm in terms of efficiency and accuracy.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117234030","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019455
Bhavnesh Kumar, Y. K. Chauhan, V. Shrivastava
In this paper, performance analysis of an induction motor drive employing a loss minimization algorithm (LMA) is presented. As the induction motors are not designed to impart high efficiency under partial loading conditions, proposed LMA is used to improve the efficiency under such load conditions. For the efficiency improvement LMA uses the rotor flux as a control variable. Mathematical model of induction motor in field-oriented frame, including proposed loss model is derived. The complete drive system is simulated in MATLAB/Simulink software for different operating conditions. Simulation results obtained shows the effectiveness of the proposed algorithm in partial loading conditions.
{"title":"Performance analysis of induction motor drive with optimal rotor flux for energy efficient operation","authors":"Bhavnesh Kumar, Y. K. Chauhan, V. Shrivastava","doi":"10.1109/ICACCCT.2014.7019455","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019455","url":null,"abstract":"In this paper, performance analysis of an induction motor drive employing a loss minimization algorithm (LMA) is presented. As the induction motors are not designed to impart high efficiency under partial loading conditions, proposed LMA is used to improve the efficiency under such load conditions. For the efficiency improvement LMA uses the rotor flux as a control variable. Mathematical model of induction motor in field-oriented frame, including proposed loss model is derived. The complete drive system is simulated in MATLAB/Simulink software for different operating conditions. Simulation results obtained shows the effectiveness of the proposed algorithm in partial loading conditions.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124098656","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019195
J. C. Vijayshree, T. G. Palanivelu
Nowadays due to the increase in demand for various multimedia services requiring high capacity, shortage of wireless resources becomes a serious problem in cellular networks. It is difficult to suddenly increase the capacity of wireless communication networks because of high cost and complexity. In order to increase the capacity of wireless communication networks with minor changes and low cost, internetworking is needed. The main objective of SIP is to support the upper layer and mobility management protocols to optimize the handover process between heterogeneous networks such as Ethernet, Bluetooth, Wi-Fi, WiMAX, 802.11 and various other networks. The basic purpose of the SIP standard is to facilitate between heterogeneous networks to provide seamless mobility. This standard also supports handover for the both mobile as well as stationary users. For mobile users, handover can occur when wireless link condition changes due to Mobile Node (MN) movement. In this proposed work, Vertical handover is implemented between WLAN and WiMAX networks by using Session initiation protocol and the performance metrics such as Network delay, Neighbour advertisements, Handover delay and throughput were obtained.
{"title":"Vertical handover triggering between WLAN and WIMAX using sip","authors":"J. C. Vijayshree, T. G. Palanivelu","doi":"10.1109/ICACCCT.2014.7019195","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019195","url":null,"abstract":"Nowadays due to the increase in demand for various multimedia services requiring high capacity, shortage of wireless resources becomes a serious problem in cellular networks. It is difficult to suddenly increase the capacity of wireless communication networks because of high cost and complexity. In order to increase the capacity of wireless communication networks with minor changes and low cost, internetworking is needed. The main objective of SIP is to support the upper layer and mobility management protocols to optimize the handover process between heterogeneous networks such as Ethernet, Bluetooth, Wi-Fi, WiMAX, 802.11 and various other networks. The basic purpose of the SIP standard is to facilitate between heterogeneous networks to provide seamless mobility. This standard also supports handover for the both mobile as well as stationary users. For mobile users, handover can occur when wireless link condition changes due to Mobile Node (MN) movement. In this proposed work, Vertical handover is implemented between WLAN and WiMAX networks by using Session initiation protocol and the performance metrics such as Network delay, Neighbour advertisements, Handover delay and throughput were obtained.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128326749","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 : 2014-05-08DOI: 10.1109/ICACCCT.2014.7019342
P. Suba, B. Bharathi
The Automatic Speaker Recognition (ASR) is to identify information about the particular speaker identification. The actual goal is to possess machine automatically to recognize a person or perhaps to authenticate a persons claimed identity through his/her speech. This paper proposes the speaker identification task using different short term and long term features. The short term features are extracted based on frames. This represents the characteristics of speech signal with reduced redundancy. In training phase, various short-term features such as Mel Frequency Cepstral Coefficient(MFCC), Linear Predictive Cepstral Coefficient(LPCC), Perceptual Linear Predictive(PLP) extracted and modeled using Gaussian Mixture Models(GMM). The long term features like prosody are used to identify the speaking behavior. The long term features are often obtained on portions of speech signal longer than one frame. Long term feature are extracted from the speech signal and trained using Gaussian mixture models. The different short term and long term features are extracted separately and the combination of them are also extracted and modeled using Gaussian Mixture Models(GMM) to get the target model. In testing phase, the features are extracted from the given test speech signal at different duration of time. This extracted features are given to the stated speaker design and the decisions are obtained. Finally, the overall performance are examined according to the combination of short-term and long term-features.
{"title":"Analysing the performance of speaker identification task using different short term and long term features","authors":"P. Suba, B. Bharathi","doi":"10.1109/ICACCCT.2014.7019342","DOIUrl":"https://doi.org/10.1109/ICACCCT.2014.7019342","url":null,"abstract":"The Automatic Speaker Recognition (ASR) is to identify information about the particular speaker identification. The actual goal is to possess machine automatically to recognize a person or perhaps to authenticate a persons claimed identity through his/her speech. This paper proposes the speaker identification task using different short term and long term features. The short term features are extracted based on frames. This represents the characteristics of speech signal with reduced redundancy. In training phase, various short-term features such as Mel Frequency Cepstral Coefficient(MFCC), Linear Predictive Cepstral Coefficient(LPCC), Perceptual Linear Predictive(PLP) extracted and modeled using Gaussian Mixture Models(GMM). The long term features like prosody are used to identify the speaking behavior. The long term features are often obtained on portions of speech signal longer than one frame. Long term feature are extracted from the speech signal and trained using Gaussian mixture models. The different short term and long term features are extracted separately and the combination of them are also extracted and modeled using Gaussian Mixture Models(GMM) to get the target model. In testing phase, the features are extracted from the given test speech signal at different duration of time. This extracted features are given to the stated speaker design and the decisions are obtained. Finally, the overall performance are examined according to the combination of short-term and long term-features.","PeriodicalId":239918,"journal":{"name":"2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128419704","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：