Pub Date : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993034
K. Sandeep, R. Thilagavathy
Long Term Evolution (LTE) of the Universal Mobile Telecommunication System (UMTS) is a 3rd Generation Partnership Project (3GPP). It is a 3.9 Generation (3.9G) Radio Access Standard, but it is advertised as 4th Generation (4G) by Mobile Carriers. The control information is transmitted to the user equipment (UE) present in the cell through Physical Downlink Control Channel (PDCCH). This paper deals with the implementation of PDCCH Transmitter and Receiver by employing QPSK and 16QAM as modulation schemes. 16QAM modulation improves performance and reduces the power consumption when compared to QPSK. The result analysis displays improvement in frequency and reduction of power consumption. The design is simulated in Modelsim 6.3g and implemented in CMOS 180nm technology using Cadence RTL Compiler.
{"title":"Performance comparison of physical downlink control channel (PDCCH) for LTE employing QPSK and 16QAM as modulation schemes","authors":"K. Sandeep, R. Thilagavathy","doi":"10.1109/ICCICCT.2014.6993034","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993034","url":null,"abstract":"Long Term Evolution (LTE) of the Universal Mobile Telecommunication System (UMTS) is a 3rd Generation Partnership Project (3GPP). It is a 3.9 Generation (3.9G) Radio Access Standard, but it is advertised as 4th Generation (4G) by Mobile Carriers. The control information is transmitted to the user equipment (UE) present in the cell through Physical Downlink Control Channel (PDCCH). This paper deals with the implementation of PDCCH Transmitter and Receiver by employing QPSK and 16QAM as modulation schemes. 16QAM modulation improves performance and reduces the power consumption when compared to QPSK. The result analysis displays improvement in frequency and reduction of power consumption. The design is simulated in Modelsim 6.3g and implemented in CMOS 180nm technology using Cadence RTL Compiler.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"23 1","pages":"608-613"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82103338","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993089
Wasundhara D. Paliwal, P. Shastry
To reduced area and power in synchronous elastic circuits we are using combinations of various elasticity approaches. Elasticity refers to the property of a circuit in which circuits can tolerate arbitrary latency/delay variations in their computation units as well as communication channels. Elasticity does not make any assumption about the specific implementation of the circuit. This paper investigates different optimization approaches to reduce these area and power overheads of elastic control network without sacrificing the control network performance. Ultra simple fork (USFork), early evaluation join (EEJoin), half-buffer retiming (HBR) controller, eager Fork, join, lazy fork combinations for implementation are introduced. In this approach we check all node and all combinational blocks clock period and uses elastic buffer only when it needed. Comparing to published work on a Minimips processor case study[3] and Synchronous elasticization at reduced cost[2], our implementation shows up 8% and 15.08% area and power due to proposed flow of implementing synchronous elasticization with 17.5 % increase in throughput i.e. 0.94 Gbits/sec.
{"title":"Synchronous elastic circuit with higher throughput at reduced area and power","authors":"Wasundhara D. Paliwal, P. Shastry","doi":"10.1109/ICCICCT.2014.6993089","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993089","url":null,"abstract":"To reduced area and power in synchronous elastic circuits we are using combinations of various elasticity approaches. Elasticity refers to the property of a circuit in which circuits can tolerate arbitrary latency/delay variations in their computation units as well as communication channels. Elasticity does not make any assumption about the specific implementation of the circuit. This paper investigates different optimization approaches to reduce these area and power overheads of elastic control network without sacrificing the control network performance. Ultra simple fork (USFork), early evaluation join (EEJoin), half-buffer retiming (HBR) controller, eager Fork, join, lazy fork combinations for implementation are introduced. In this approach we check all node and all combinational blocks clock period and uses elastic buffer only when it needed. Comparing to published work on a Minimips processor case study[3] and Synchronous elasticization at reduced cost[2], our implementation shows up 8% and 15.08% area and power due to proposed flow of implementing synchronous elasticization with 17.5 % increase in throughput i.e. 0.94 Gbits/sec.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"7 1","pages":"917-922"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81736037","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993069
J. Jaleel, Sibi Salim, S. Archana
Computer Aided Diagnosis (CAD) could be applied as a solution to reduce the chances of human errors and helps Medical Practioners in the correct classification of Breast Masses. This paper emphasizes an algorithm for the early de tection of breast masses. Textural analysis is one of the efficient methods for the early detection of abnormalities. The paper enumerates an efficient Discrete Wavelet Transform (DWT) algorithm and a modified Grey-Level Co-Occurrence Matrix (GLCM) method for textural feature extraction from segmented mammogram images. Each tissue pattern after classification is characterized into Benign and Malignant masses. A total of 148 mammogram images were taken from Mini MIAS database and solid breast nodules were classified into benign and malignant masses using supervised classifiers. The classifier used is Radial Basis Function Neural Network (RBFNN). The proposed system has a high potential for cancer detection from digitized screening mammograms.
{"title":"Textural features based computer aided diagnostic system for mammogram mass classification","authors":"J. Jaleel, Sibi Salim, S. Archana","doi":"10.1109/ICCICCT.2014.6993069","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993069","url":null,"abstract":"Computer Aided Diagnosis (CAD) could be applied as a solution to reduce the chances of human errors and helps Medical Practioners in the correct classification of Breast Masses. This paper emphasizes an algorithm for the early de tection of breast masses. Textural analysis is one of the efficient methods for the early detection of abnormalities. The paper enumerates an efficient Discrete Wavelet Transform (DWT) algorithm and a modified Grey-Level Co-Occurrence Matrix (GLCM) method for textural feature extraction from segmented mammogram images. Each tissue pattern after classification is characterized into Benign and Malignant masses. A total of 148 mammogram images were taken from Mini MIAS database and solid breast nodules were classified into benign and malignant masses using supervised classifiers. The classifier used is Radial Basis Function Neural Network (RBFNN). The proposed system has a high potential for cancer detection from digitized screening mammograms.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"26 1","pages":"806-811"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84140454","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993117
U. Kumaran, R. Shaji
Reliability and timely information delivery are highly concerned factors in Vehicular ad-hoc network. A better handover mechanism plays an important role in the handover process between the vehicle nodes during the vehicles on the road. Vertical handover is very much essential to ensure service continuity in Vehicular Ad-hoc network. When we compared with conventional handover decision taken by single criteria, multi criteria decision methods reduce handover rate and effectively utilizing the usage of network resources. In Vehicular Ad-hoc Network continuous connectivity is a great challenge, because of vehicles speed and ever changing topology of the network. In VANET vehicles can communicate through Vehicle-to-Vehicle communication mode and Vehicle-to-Infrastructure communication mode. Users in the vehicular network can access internet while on the move from one place to another with V2I. Due to heterogeneous wireless access, vertical handover is needed to maintain continuous connectivity between the vehicles and infrastructures. In this paper advanced methods of vertical handover decision algorithm is used to select best available network by comparing multiple parameter values (such as network traffic and vehicle speed). The algorithm is evaluated by assessing the performance through the number of handoff occurs, throughput gained and level of latency attained. The performance of the simulation shows that the number of handover and latency can be minimized where as throughput can be maximized, if we consider vehicle speed and network traffic parameters for taking handover decision process.
{"title":"Vertical handover in Vehicular ad-hoc network using multiple parameters","authors":"U. Kumaran, R. Shaji","doi":"10.1109/ICCICCT.2014.6993117","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993117","url":null,"abstract":"Reliability and timely information delivery are highly concerned factors in Vehicular ad-hoc network. A better handover mechanism plays an important role in the handover process between the vehicle nodes during the vehicles on the road. Vertical handover is very much essential to ensure service continuity in Vehicular Ad-hoc network. When we compared with conventional handover decision taken by single criteria, multi criteria decision methods reduce handover rate and effectively utilizing the usage of network resources. In Vehicular Ad-hoc Network continuous connectivity is a great challenge, because of vehicles speed and ever changing topology of the network. In VANET vehicles can communicate through Vehicle-to-Vehicle communication mode and Vehicle-to-Infrastructure communication mode. Users in the vehicular network can access internet while on the move from one place to another with V2I. Due to heterogeneous wireless access, vertical handover is needed to maintain continuous connectivity between the vehicles and infrastructures. In this paper advanced methods of vertical handover decision algorithm is used to select best available network by comparing multiple parameter values (such as network traffic and vehicle speed). The algorithm is evaluated by assessing the performance through the number of handoff occurs, throughput gained and level of latency attained. The performance of the simulation shows that the number of handover and latency can be minimized where as throughput can be maximized, if we consider vehicle speed and network traffic parameters for taking handover decision process.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"30 1","pages":"1059-1064"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84443302","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993011
Dablu Kumar, B. Champaty, K. Uvanesh, K. Pal, A. Anis
In the last decade, there has been an exponential increase in the research being carried out on wearable devices. The research on wearable devices still in its nascent stages and hence there are not many commercial devices available for improving the lifestyle of the differently-abled persons. Hence, in this study, we have made an attempt to device a wearable electronic travelling aid for the blinds using IR based distance monitoring sensors. The device has been designed to generate audio signals to alarm the user about the presence of an obstacle. The user can manipulate the device to have information about the aerial obstacles. 10 volunteers were trained on the device who reported that the device was user-friendly.
{"title":"Designing of an infra-red optocoupler based mobility aid for the blinds","authors":"Dablu Kumar, B. Champaty, K. Uvanesh, K. Pal, A. Anis","doi":"10.1109/ICCICCT.2014.6993011","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993011","url":null,"abstract":"In the last decade, there has been an exponential increase in the research being carried out on wearable devices. The research on wearable devices still in its nascent stages and hence there are not many commercial devices available for improving the lifestyle of the differently-abled persons. Hence, in this study, we have made an attempt to device a wearable electronic travelling aid for the blinds using IR based distance monitoring sensors. The device has been designed to generate audio signals to alarm the user about the presence of an obstacle. The user can manipulate the device to have information about the aerial obstacles. 10 volunteers were trained on the device who reported that the device was user-friendly.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"33 1","pages":"486-490"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81412481","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993024
R. Ramadevi
Currently various types of wavelet transform are widely used in analysis of signals of different type. Mainly wavelet transform widely used to separate different types of information contained in original signals. Wavelet transform can be used to extract the features even in different scales. These features are able to characterize signals in different resolutions. As a case study, the discrete wavelet transform approach to diagnose cavitation signal associated with centrifugal pump cavitation test rig has been considered. Mean value of coefficients as feature can be extracted from various decomposition levels, variations of mean value with cavitation states are observed.
{"title":"Cavitation signal analysis using discrete wavelet transform","authors":"R. Ramadevi","doi":"10.1109/ICCICCT.2014.6993024","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993024","url":null,"abstract":"Currently various types of wavelet transform are widely used in analysis of signals of different type. Mainly wavelet transform widely used to separate different types of information contained in original signals. Wavelet transform can be used to extract the features even in different scales. These features are able to characterize signals in different resolutions. As a case study, the discrete wavelet transform approach to diagnose cavitation signal associated with centrifugal pump cavitation test rig has been considered. Mean value of coefficients as feature can be extracted from various decomposition levels, variations of mean value with cavitation states are observed.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"47 1","pages":"558-560"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83367588","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993000
A. Anwar, D. Menaka
The presence of large number of spectral bands in the remote sensing images results in difficulty of identifying various land cover regions. Land cover classification is one of the recent researches which find more application in satellite image processing. It is important to recognize different land classes from a multispectral satellite image as the raw image contains noises and less clarity. The work was done in three stages such as preprocessing, feature extraction and classification. Noise present in the images are removed using a non-local means filter in preprocessing. Gabor wavelet and GLCM (gray level co-occurrence matrix) techniques were compared for feature extraction where PCA uses better in dimension reduction. The proposed sparse classifier efficiently classifies the given multispectral satellite image. It identifies the scattering features of same group of textures in the image, produces better accuracy compared to other techniques.
{"title":"Land cover image classification using adaptive sparse fusion classifier","authors":"A. Anwar, D. Menaka","doi":"10.1109/ICCICCT.2014.6993000","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993000","url":null,"abstract":"The presence of large number of spectral bands in the remote sensing images results in difficulty of identifying various land cover regions. Land cover classification is one of the recent researches which find more application in satellite image processing. It is important to recognize different land classes from a multispectral satellite image as the raw image contains noises and less clarity. The work was done in three stages such as preprocessing, feature extraction and classification. Noise present in the images are removed using a non-local means filter in preprocessing. Gabor wavelet and GLCM (gray level co-occurrence matrix) techniques were compared for feature extraction where PCA uses better in dimension reduction. The proposed sparse classifier efficiently classifies the given multispectral satellite image. It identifies the scattering features of same group of textures in the image, produces better accuracy compared to other techniques.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"26 1","pages":"431-434"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87297358","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6992960
J. Ramya, B. Parvathavarthini
Visual Cryptography is a special kind of cryptographic technique in which the decryption can perform by the human visual capability. In general, for some critical security issue the visual cryptography scheme is used, for example to identify the difference in human and machine. Similarly some other applications also use the visual cryptography schemes like scanning and printing, captcha etc. Hence the researchers developed many methods and techniques for the visual cryptography schemes. This paper is intended to study the various visual cryptography schemes and also to analysis the performance on the basis of expansion of pixel, number of secret images, image format and type of share generated. In addition we present a concise description about the instructions for future research.
{"title":"An extensive review on visual cryptography schemes","authors":"J. Ramya, B. Parvathavarthini","doi":"10.1109/ICCICCT.2014.6992960","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6992960","url":null,"abstract":"Visual Cryptography is a special kind of cryptographic technique in which the decryption can perform by the human visual capability. In general, for some critical security issue the visual cryptography scheme is used, for example to identify the difference in human and machine. Similarly some other applications also use the visual cryptography schemes like scanning and printing, captcha etc. Hence the researchers developed many methods and techniques for the visual cryptography schemes. This paper is intended to study the various visual cryptography schemes and also to analysis the performance on the basis of expansion of pixel, number of secret images, image format and type of share generated. In addition we present a concise description about the instructions for future research.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"27 1","pages":"223-228"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86526620","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6992997
Aida S. Tharakan, B. Mathew
Built-in-self-test (BIST) has emerged as a promising solution to VLS I testing problems. The test pattern generation scheme using twisted-ring-counters is more efficient than the pseudo random testing method in detecting random-pattern-resistant faults. Related work based on single fixed-order twisted-ring-counter design requires long test time to achieve high fault coverage and large storage space to store the seeds and the control data. By using multiple programmable twisted-ring-counters (PTRC), a significant reduction in test application cycles were achieved. In this paper, a reconfigurable programmable multiple twisted-ring-counter is proposed to minimize the test time and to generate more number of different test patterns. Here the programmable twisted-ring-counter operates depending on the control signal of the block select module, thus we can generate more number of patterns with less time. The design was modeled in VHDL and simulated using Modelsim SE 6.2 b simulator. Synthesis was done using Xilinx IS E 14.2.
内置自检(BIST)已成为解决VLS I测试问题的一种很有前途的解决方案。采用扭转环计数器的测试模式生成方案在检测抗随机模式故障方面比伪随机测试方法更有效。基于单定阶扭环计数器设计的相关工作需要较长的测试时间来实现高故障覆盖率，需要较大的存储空间来存储种子和控制数据。通过使用多个可编程扭环计数器(PTRC)，测试应用周期显著缩短。本文提出了一种可重构的可编程多重扭环计数器，以减少测试时间和产生更多不同的测试模式。在这里，可编程的扭环计数器根据模块选择模块的控制信号进行操作，因此我们可以用更少的时间生成更多的图案。采用VHDL语言对设计进行建模，并使用Modelsim SE 6.2 b模拟器进行仿真。采用Xilinx IS E 14.2合成。
{"title":"On-chip test generation scheme based on reconfigurable programmable and multiple twisted-ring counters","authors":"Aida S. Tharakan, B. Mathew","doi":"10.1109/ICCICCT.2014.6992997","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6992997","url":null,"abstract":"Built-in-self-test (BIST) has emerged as a promising solution to VLS I testing problems. The test pattern generation scheme using twisted-ring-counters is more efficient than the pseudo random testing method in detecting random-pattern-resistant faults. Related work based on single fixed-order twisted-ring-counter design requires long test time to achieve high fault coverage and large storage space to store the seeds and the control data. By using multiple programmable twisted-ring-counters (PTRC), a significant reduction in test application cycles were achieved. In this paper, a reconfigurable programmable multiple twisted-ring-counter is proposed to minimize the test time and to generate more number of different test patterns. Here the programmable twisted-ring-counter operates depending on the control signal of the block select module, thus we can generate more number of patterns with less time. The design was modeled in VHDL and simulated using Modelsim SE 6.2 b simulator. Synthesis was done using Xilinx IS E 14.2.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"49 1","pages":"414-418"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86439972","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 : 2014-07-10DOI: 10.1109/ICCICCT.2014.6993171
N. Radha, A. Shahina, G. Vinoth, A. N. Khan
The performance of Automatic Speech recognition system (ASR) built using close talk microphones degrades in noisy environments. AS R built using Throat Microphone (TM) speech shows relatively better performance under such adverse situations. However, some of the sounds are not well captured in TM. In this work we explore the combined use of Normal Microphone (NM) and TM features to improve the recognition rate of AS R. In the proposed work, the combined Mel-Frequency Cepstral Coefficients (MFCC) derived from the two signals are used to built an AS R in the HMM framework to recognize the 145 syllabic units of Indian language Hindi. The performance of this combined AS R system shows a significant improvement in performance when compared with individual AS R systems built using NM and TM features, respectively.
{"title":"Improving recognition of syallabic units of Hindi languagae using combined features of Throat Microphone and Normal Microphone speech","authors":"N. Radha, A. Shahina, G. Vinoth, A. N. Khan","doi":"10.1109/ICCICCT.2014.6993171","DOIUrl":"https://doi.org/10.1109/ICCICCT.2014.6993171","url":null,"abstract":"The performance of Automatic Speech recognition system (ASR) built using close talk microphones degrades in noisy environments. AS R built using Throat Microphone (TM) speech shows relatively better performance under such adverse situations. However, some of the sounds are not well captured in TM. In this work we explore the combined use of Normal Microphone (NM) and TM features to improve the recognition rate of AS R. In the proposed work, the combined Mel-Frequency Cepstral Coefficients (MFCC) derived from the two signals are used to built an AS R in the HMM framework to recognize the 145 syllabic units of Indian language Hindi. The performance of this combined AS R system shows a significant improvement in performance when compared with individual AS R systems built using NM and TM features, respectively.","PeriodicalId":6615,"journal":{"name":"2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT)","volume":"9 1","pages":"1343-1348"},"PeriodicalIF":0.0,"publicationDate":"2014-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86796320","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：