Pub Date : 2011-12-01DOI: 10.1109/WICT.2011.6141229
T. Gopalakrishnan, S. Ramakrishnan, K. Balasamy, A.S. Muthananda Murugavel
In this paper, the requirements, techniques and applications of digital watermarking for high-quality images were discussed. The several classes of digital watermarking techniques defined by their appearance and application domains specify the requirements and summarize the current research efforts in the image applications. An optimal watermark embedding method is developed to achieve minimum watermarking distortion. A secret embedding key is designed to securely embed the fragile watermarks so that the method is robust to counterfeiting, even when the malicious attackers are fully aware of the watermark embedding algorithm. For robustness this algorithm should resist all kinds of attacks, such as common signal processing operators, geometric attacks and so on.
{"title":"Semi fragile watermarking using Gaussian mixture model for malicious image attacks","authors":"T. Gopalakrishnan, S. Ramakrishnan, K. Balasamy, A.S. Muthananda Murugavel","doi":"10.1109/WICT.2011.6141229","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141229","url":null,"abstract":"In this paper, the requirements, techniques and applications of digital watermarking for high-quality images were discussed. The several classes of digital watermarking techniques defined by their appearance and application domains specify the requirements and summarize the current research efforts in the image applications. An optimal watermark embedding method is developed to achieve minimum watermarking distortion. A secret embedding key is designed to securely embed the fragile watermarks so that the method is robust to counterfeiting, even when the malicious attackers are fully aware of the watermark embedding algorithm. For robustness this algorithm should resist all kinds of attacks, such as common signal processing operators, geometric attacks and so on.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126472950","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141236
G. Govindan, A. Nair
It is widely recognized that the information from the amino acid sequence can serve as crucial pointers in predicting subcellular location of proteins. We introduce a new feature vector for predicting proteins targeted to various compartments in the intracellular and secretory pathway from protein sequence. Features are based on the global Composition, Transition and Distribution (CTD) of amino acid attributes such as hydrophobicity, normalized van der Waals volume, polarity, polarizability, charge, secondary structure and solvent accessibility. Sequences are considered in three equal parts and the features are extracted separately for all the three parts. Based on the feature vectors, we have trained a Support Vector Machine to classify intracellular and secretory proteins. Our method gives an accuracy of 92% in human, 88% in plant and 95% in fungi with independent dataset at root level of the protein sorting pathway.
{"title":"Classification of proteins in intracellular and secretory pathway using global descriptors of amino acid sequence","authors":"G. Govindan, A. Nair","doi":"10.1109/WICT.2011.6141236","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141236","url":null,"abstract":"It is widely recognized that the information from the amino acid sequence can serve as crucial pointers in predicting subcellular location of proteins. We introduce a new feature vector for predicting proteins targeted to various compartments in the intracellular and secretory pathway from protein sequence. Features are based on the global Composition, Transition and Distribution (CTD) of amino acid attributes such as hydrophobicity, normalized van der Waals volume, polarity, polarizability, charge, secondary structure and solvent accessibility. Sequences are considered in three equal parts and the features are extracted separately for all the three parts. Based on the feature vectors, we have trained a Support Vector Machine to classify intracellular and secretory proteins. Our method gives an accuracy of 92% in human, 88% in plant and 95% in fungi with independent dataset at root level of the protein sorting pathway.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128963107","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141398
Vinod Kumar, J. Sachdeva, I. Gupta, N. Khandelwal, C. Ahuja
The present study is conducted to assist radiologists in marking tumor boundaries and in decision making process for multiclass classification of brain tumors. Primary brain tumors and secondary brain tumors along with normal regions are segmented by Gradient Vector Flow (GVF)-a boundary based technique. GVF is a user interactive model for extracting tumor boundaries. These segmented regions of interest (ROIs) are than classified by using Principal Component Analysis-Artificial Neural Network (PCA-ANN) approach. The study is performed on diversified dataset of 856 ROIs from 428 post contrast T1- weighted MR images of 55 patients. 218 texture and intensity features are extracted from ROIs. PCA is used for reduction of dimensionality of the feature space. Six classes which include primary tumors such as Astrocytoma (AS), Glioblastoma Multiforme (GBM), child tumor-Medulloblastoma (MED) and Meningioma (MEN), secondary tumor-Metastatic (MET) along with normal regions (NR) are discriminated using ANN. Test results show that the PCA-ANN approach has enhanced the overall accuracy of ANN from 72.97 % to 95.37%. The proposed method has delivered a high accuracy for each class: AS-90.74%, GBM-88.46%, MED-85.00%, MEN-90.70%, MET-96.67%and NR-93.78%. It is observed that PCA-ANN provides better results than the existing methods.
{"title":"Classification of brain tumors using PCA-ANN","authors":"Vinod Kumar, J. Sachdeva, I. Gupta, N. Khandelwal, C. Ahuja","doi":"10.1109/WICT.2011.6141398","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141398","url":null,"abstract":"The present study is conducted to assist radiologists in marking tumor boundaries and in decision making process for multiclass classification of brain tumors. Primary brain tumors and secondary brain tumors along with normal regions are segmented by Gradient Vector Flow (GVF)-a boundary based technique. GVF is a user interactive model for extracting tumor boundaries. These segmented regions of interest (ROIs) are than classified by using Principal Component Analysis-Artificial Neural Network (PCA-ANN) approach. The study is performed on diversified dataset of 856 ROIs from 428 post contrast T1- weighted MR images of 55 patients. 218 texture and intensity features are extracted from ROIs. PCA is used for reduction of dimensionality of the feature space. Six classes which include primary tumors such as Astrocytoma (AS), Glioblastoma Multiforme (GBM), child tumor-Medulloblastoma (MED) and Meningioma (MEN), secondary tumor-Metastatic (MET) along with normal regions (NR) are discriminated using ANN. Test results show that the PCA-ANN approach has enhanced the overall accuracy of ANN from 72.97 % to 95.37%. The proposed method has delivered a high accuracy for each class: AS-90.74%, GBM-88.46%, MED-85.00%, MEN-90.70%, MET-96.67%and NR-93.78%. It is observed that PCA-ANN provides better results than the existing methods.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127226385","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141426
Tibebe Beshah, D. Ejigu, A. Abraham, V. Snás̃el, P. Kromer
This research tries to view accident data collection and analysis as a system that requires a special view towards understanding the whole and making sense out of it for improved decision making in the effort of reducing the problem of road safety. Under the umbrella of an information architecture research for road safety in developing countries, the objective of this machine learning experimental research is to explore and predict the role of road users on possible injury risks. The research employed Classification and Adaptive Regression Trees (CART) and RandomForest approaches. To identify relevant patterns and illustrate the performance of the techniques for the road safety domain, road accident data collected from Addis Ababa Traffic Office is exposed to many sided analyses. Empirical results showed that the models could classify accidents with promising accuracy.
{"title":"Pattern recognition and knowledge discovery from road traffic accident data in Ethiopia: Implications for improving road safety","authors":"Tibebe Beshah, D. Ejigu, A. Abraham, V. Snás̃el, P. Kromer","doi":"10.1109/WICT.2011.6141426","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141426","url":null,"abstract":"This research tries to view accident data collection and analysis as a system that requires a special view towards understanding the whole and making sense out of it for improved decision making in the effort of reducing the problem of road safety. Under the umbrella of an information architecture research for road safety in developing countries, the objective of this machine learning experimental research is to explore and predict the role of road users on possible injury risks. The research employed Classification and Adaptive Regression Trees (CART) and RandomForest approaches. To identify relevant patterns and illustrate the performance of the techniques for the road safety domain, road accident data collected from Addis Ababa Traffic Office is exposed to many sided analyses. Empirical results showed that the models could classify accidents with promising accuracy.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117214907","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141429
Ravindra Singh, M. Hanumandlu, S. Khatoon, I. Ibraheem
The design, operation and control of stabilization - tracking systems has been a challenging task for the scientists and engineers with the present day requirements of modern aged sophistication of these systems. The conventional control concepts have been outplayed by the optimal control techniques with the evolution of the modern control theory. Moreover, due to the problems associated with modern control techniques have motivated the engineers to apply intelligent technique to circumvent these difficulties. An attempt has been made to design and feasibility of an adaptive Particle Swarm Optimization (PSO) based fuzzy logic controller for stabilization-tracking system. The simulation results obtained in the study demonstrate the feasibility of the designed controllers.
{"title":"An Adaptive Particle Swarm Optimization based fuzzy logic controller for line of sight stabilization tracking and pointing application","authors":"Ravindra Singh, M. Hanumandlu, S. Khatoon, I. Ibraheem","doi":"10.1109/WICT.2011.6141429","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141429","url":null,"abstract":"The design, operation and control of stabilization - tracking systems has been a challenging task for the scientists and engineers with the present day requirements of modern aged sophistication of these systems. The conventional control concepts have been outplayed by the optimal control techniques with the evolution of the modern control theory. Moreover, due to the problems associated with modern control techniques have motivated the engineers to apply intelligent technique to circumvent these difficulties. An attempt has been made to design and feasibility of an adaptive Particle Swarm Optimization (PSO) based fuzzy logic controller for stabilization-tracking system. The simulation results obtained in the study demonstrate the feasibility of the designed controllers.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117281821","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141312
Sahana Bhosale, R. Daruwala
In broadband wireless access network, continuous high speed data communication can be provided to mobile subscribers by well designed mobility management, where handover is a key element in maintaining air link to base station even in high velocity. When a mobile station changes its geographical position, it may also need to change its attachment point in the network in order to retain the quality of the connection. Currently, the mobility of a terminal is a requirement of great importance, supported by a procedure known as handover. Horizontal Handover (HHO) is a symmetric process and happens within the same technology e.g between different Wifi cells. If it is executed between different technologies, for example, WiMAX to Wi-Fi, then it is called vertical HO. In this paper, initially we have investigated the performance of horizontal handovers within Wifi cells and then that of vertical handover between Wi-Fi and WiMAX. Evaluation of packet loss is done while transferring constant bit rate traffic (CBR) for UDP protocol This experiment can be used for academic purpose to help students understand the concept of handover.
{"title":"Experimental analysis of horizontal and vertical handovers in wireless access networks using NS2","authors":"Sahana Bhosale, R. Daruwala","doi":"10.1109/WICT.2011.6141312","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141312","url":null,"abstract":"In broadband wireless access network, continuous high speed data communication can be provided to mobile subscribers by well designed mobility management, where handover is a key element in maintaining air link to base station even in high velocity. When a mobile station changes its geographical position, it may also need to change its attachment point in the network in order to retain the quality of the connection. Currently, the mobility of a terminal is a requirement of great importance, supported by a procedure known as handover. Horizontal Handover (HHO) is a symmetric process and happens within the same technology e.g between different Wifi cells. If it is executed between different technologies, for example, WiMAX to Wi-Fi, then it is called vertical HO. In this paper, initially we have investigated the performance of horizontal handovers within Wifi cells and then that of vertical handover between Wi-Fi and WiMAX. Evaluation of packet loss is done while transferring constant bit rate traffic (CBR) for UDP protocol This experiment can be used for academic purpose to help students understand the concept of handover.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"17a 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128190910","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141303
L. Vardharaj, Sumit Ranjan, Parampreet Singh, Narendran Rajagopalan, C. Mala
The rapidly increasing volumes of structural data of proteins has led to need of algorithms which can rapidly predict functions for proteins based on structure. Similarity between protein structures can provide evidence of possible functional similarity. In this paper, an attempt is made to efficiently recognize similar protein structures in the protein database contain thousands of proteins. This paper gives an efficient heuristic algorithm for finding protein 3D substructures in a 3D protein structure that are similar to a given query 3D protein substructure. This algorithm can be used for searching a database of protein 3D structures. Our approach is to divide the protein structure into sub-structures of size of query structure and compare each sub structure with the query protein using Procrustes algorithm which is based on the root mean square distance between the structures. The division involves constructing a bounding box over both the query and protein structure and dividing the bigger box into sizes of the smaller box. The above algorithm is implemented in parallel using message passing interface. Experiments show that our algorithm can find similar 3D substructures in reasonable time. This paper also presents various statistics as how our algorithm performs against a sequential algorithm and how the algorithm performs with varying sizes of the query structure.
{"title":"A novel approach to protein substructure matching","authors":"L. Vardharaj, Sumit Ranjan, Parampreet Singh, Narendran Rajagopalan, C. Mala","doi":"10.1109/WICT.2011.6141303","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141303","url":null,"abstract":"The rapidly increasing volumes of structural data of proteins has led to need of algorithms which can rapidly predict functions for proteins based on structure. Similarity between protein structures can provide evidence of possible functional similarity. In this paper, an attempt is made to efficiently recognize similar protein structures in the protein database contain thousands of proteins. This paper gives an efficient heuristic algorithm for finding protein 3D substructures in a 3D protein structure that are similar to a given query 3D protein substructure. This algorithm can be used for searching a database of protein 3D structures. Our approach is to divide the protein structure into sub-structures of size of query structure and compare each sub structure with the query protein using Procrustes algorithm which is based on the root mean square distance between the structures. The division involves constructing a bounding box over both the query and protein structure and dividing the bigger box into sizes of the smaller box. The above algorithm is implemented in parallel using message passing interface. Experiments show that our algorithm can find similar 3D substructures in reasonable time. This paper also presents various statistics as how our algorithm performs against a sequential algorithm and how the algorithm performs with varying sizes of the query structure.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133418551","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141270
Jyoti Gupta, A. Sangal, Hemlata Verma
The performance of charge pumps depends heavily on the ability to efficiently generate high voltages on-chip while meeting stringent power and area requirements. The paper presents a High Speed CMOS charge pump circuit for PLL applications using 90nm CMOS technology that operates at 1V. The proposed circuit has simple symmetric structure and provides more stable operation while reducing spurious jump phenomenon. The experimental result shows significant improvement in overcoming the problem of jitter. The output voltage of presented design can be increased up to 1010mV. The functionality of charge pump has been tested at operating based frequency of 1000 MHz.
{"title":"High speed CMOS charge pump circuit for PLL applications using 90nm CMOS technology","authors":"Jyoti Gupta, A. Sangal, Hemlata Verma","doi":"10.1109/WICT.2011.6141270","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141270","url":null,"abstract":"The performance of charge pumps depends heavily on the ability to efficiently generate high voltages on-chip while meeting stringent power and area requirements. The paper presents a High Speed CMOS charge pump circuit for PLL applications using 90nm CMOS technology that operates at 1V. The proposed circuit has simple symmetric structure and provides more stable operation while reducing spurious jump phenomenon. The experimental result shows significant improvement in overcoming the problem of jitter. The output voltage of presented design can be increased up to 1010mV. The functionality of charge pump has been tested at operating based frequency of 1000 MHz.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131948900","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141424
A. Tripathy, J. Adinarayana, D. Sudharsan, S. Merchant, U. Desai, K. Vijayalakshmi, D. Raji Reddy, G. Sreenivas, S. Ninomiya, M. Hirafuji, T. Kiura, K. Tanaka
Data driven precision agriculture aspects, particularly the pest/disease management, require a dynamic crop-weather data. An experiment was conducted in a semi-arid region to understand the crop-weather-pest/disease relations using wireless sensory and field-level surveillance data on closely related and interdependent pest (Thrips) - disease (Bud Necrosis) dynamics of groundnut crop. Data mining techniques were used to turn the data into useful information/knowledge/relations/trends and correlation of crop-weather-pest/disease continuum. These dynamics obtained from the data mining techniques and trained through mathematical models were validated with corresponding surveillance data. Results obtained from 2009 & 2010 kharif seasons (monsoon) and 2009–10 & 2010–11 rabi seasons (post monsoon) data could be used to develop a real to near real-time decision support system for pest/disease predictions.
{"title":"Data mining and wireless sensor network for agriculture pest/disease predictions","authors":"A. Tripathy, J. Adinarayana, D. Sudharsan, S. Merchant, U. Desai, K. Vijayalakshmi, D. Raji Reddy, G. Sreenivas, S. Ninomiya, M. Hirafuji, T. Kiura, K. Tanaka","doi":"10.1109/WICT.2011.6141424","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141424","url":null,"abstract":"Data driven precision agriculture aspects, particularly the pest/disease management, require a dynamic crop-weather data. An experiment was conducted in a semi-arid region to understand the crop-weather-pest/disease relations using wireless sensory and field-level surveillance data on closely related and interdependent pest (Thrips) - disease (Bud Necrosis) dynamics of groundnut crop. Data mining techniques were used to turn the data into useful information/knowledge/relations/trends and correlation of crop-weather-pest/disease continuum. These dynamics obtained from the data mining techniques and trained through mathematical models were validated with corresponding surveillance data. Results obtained from 2009 & 2010 kharif seasons (monsoon) and 2009–10 & 2010–11 rabi seasons (post monsoon) data could be used to develop a real to near real-time decision support system for pest/disease predictions.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122861477","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 : 2011-12-01DOI: 10.1109/WICT.2011.6141432
Foyzul Hassan, Mohammed Rokibul Alam Kotwal, M. N. Huda
Hidden factor such as gender characteristic plays an important role on the performance of Bangla (widely used as Bengali) automatic speech recognition (ASR). If there is a suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In our previous paper, we proposed a technique of gender effects suppression that composed of two hidden Markov model (HMM)-based classifiers that focused on a gender factor. In the proposed study, we have designed a new ASR for Bangla by suppressing the gender effects, which embeds three HMM-based classifiers for corresponding male, female and geneder-independent (GI) characteristics. In an experiment on Bangla speech database prepared by us, the proposed system that incorporates GI-classifier has achieved a significant improvement of word correct rate, word accuracy and sentence correct rate in comparison with our previous method that did not incorporate GI-classifier.
{"title":"Bangla ASR design by suppressing gender factor with gender-independent and gender-based HMM classifiers","authors":"Foyzul Hassan, Mohammed Rokibul Alam Kotwal, M. N. Huda","doi":"10.1109/WICT.2011.6141432","DOIUrl":"https://doi.org/10.1109/WICT.2011.6141432","url":null,"abstract":"Hidden factor such as gender characteristic plays an important role on the performance of Bangla (widely used as Bengali) automatic speech recognition (ASR). If there is a suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In our previous paper, we proposed a technique of gender effects suppression that composed of two hidden Markov model (HMM)-based classifiers that focused on a gender factor. In the proposed study, we have designed a new ASR for Bangla by suppressing the gender effects, which embeds three HMM-based classifiers for corresponding male, female and geneder-independent (GI) characteristics. In an experiment on Bangla speech database prepared by us, the proposed system that incorporates GI-classifier has achieved a significant improvement of word correct rate, word accuracy and sentence correct rate in comparison with our previous method that did not incorporate GI-classifier.","PeriodicalId":178645,"journal":{"name":"2011 World Congress on Information and Communication Technologies","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127733269","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：