Pub Date : 2015-04-23DOI: 10.1109/RETCOMP.2015.7090795
Prashanth Kannadaguli, Vidya Bhat
We build and compare phoneme recognition systems based on Bayesian Multivariate Modeling scheme and Hidden Markov Modeling (HMM) scheme. Both models were built by using Stochastic pattern recognition and Acoustic phonetic schemes to recognise phonemes. Since our native language is Kannada, a rich South Indian Language, we have used 15 Kannada phonemes to train and test these models. Since Mel - Frequency Cepstral Coefficients (MFCC) are well known Acoustic features of speech, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.
{"title":"A comparison of Bayesian multivariate modeling and hidden Markov modeling (HMM) based approaches for automatic phoneme recognition in kannada","authors":"Prashanth Kannadaguli, Vidya Bhat","doi":"10.1109/RETCOMP.2015.7090795","DOIUrl":"https://doi.org/10.1109/RETCOMP.2015.7090795","url":null,"abstract":"We build and compare phoneme recognition systems based on Bayesian Multivariate Modeling scheme and Hidden Markov Modeling (HMM) scheme. Both models were built by using Stochastic pattern recognition and Acoustic phonetic schemes to recognise phonemes. Since our native language is Kannada, a rich South Indian Language, we have used 15 Kannada phonemes to train and test these models. Since Mel - Frequency Cepstral Coefficients (MFCC) are well known Acoustic features of speech, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.","PeriodicalId":160330,"journal":{"name":"2015 Recent and Emerging trends in Computer and Computational Sciences (RETCOMP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134005248","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 : 2015-04-23DOI: 10.1109/RETCOMP.2015.7090796
G. Chaitra, Nayan Khare
Different features are extracted for Pattern Recognition using an efficient algorithms like Scale Invariant Feature Transform, Rotation invariant Radon Transform and extracting statistical features of a texture image. Support vector machine with RBF kernel in Weka is used in this paper for classification. This paper shows method to classify the clothing texture patterns like strips, plaid, pattern less and irregular pattern. This paper also proposes a method which can be efficient method to apply for the real time natural texture patterns and colors recognition systems. This paper gives the experiments results and the proposed method to enhance the experiments accuracy in future scope.
{"title":"Feature extraction of clothing texture patterns for classification","authors":"G. Chaitra, Nayan Khare","doi":"10.1109/RETCOMP.2015.7090796","DOIUrl":"https://doi.org/10.1109/RETCOMP.2015.7090796","url":null,"abstract":"Different features are extracted for Pattern Recognition using an efficient algorithms like Scale Invariant Feature Transform, Rotation invariant Radon Transform and extracting statistical features of a texture image. Support vector machine with RBF kernel in Weka is used in this paper for classification. This paper shows method to classify the clothing texture patterns like strips, plaid, pattern less and irregular pattern. This paper also proposes a method which can be efficient method to apply for the real time natural texture patterns and colors recognition systems. This paper gives the experiments results and the proposed method to enhance the experiments accuracy in future scope.","PeriodicalId":160330,"journal":{"name":"2015 Recent and Emerging trends in Computer and Computational Sciences (RETCOMP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128173438","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 : 2015-04-23DOI: 10.1109/RETCOMP.2015.7090798
Kusuma Mohanchandra
In the recent years, especially during the last decade electroencephalography (EEG) based brain computer interface (BCI) have become a prevailing study of neuroscience, machine learning and rehabilitation. A BCI provides an arena for a human brain to communicate with a computer directly without the normal neurophysiologic pathways. The electrical signals of the brain, with their fast responsivity with cognitive processes are most suitable as non-motor control mediation between the human and a computer. This can serve as a communication and control channel for various applications. One of the most intriguing uses of EEG is in forensic investigation, used as a tool in lie detection. Lie detection technology has been applied increasingly to investigate and solve criminal cases. Though the contributions of neurobiological research to forensic technology remain largely hypothetical, the evidences appear promising and further research is both feasible and warranted. The brain based lie detection may veritably give solution to many complicated investigation. This paper explores the evolvement of lie detection technology, their working principles, the latest development, and the prospect of their application in forensic science.
{"title":"Criminal forensic: An application to EEG","authors":"Kusuma Mohanchandra","doi":"10.1109/RETCOMP.2015.7090798","DOIUrl":"https://doi.org/10.1109/RETCOMP.2015.7090798","url":null,"abstract":"In the recent years, especially during the last decade electroencephalography (EEG) based brain computer interface (BCI) have become a prevailing study of neuroscience, machine learning and rehabilitation. A BCI provides an arena for a human brain to communicate with a computer directly without the normal neurophysiologic pathways. The electrical signals of the brain, with their fast responsivity with cognitive processes are most suitable as non-motor control mediation between the human and a computer. This can serve as a communication and control channel for various applications. One of the most intriguing uses of EEG is in forensic investigation, used as a tool in lie detection. Lie detection technology has been applied increasingly to investigate and solve criminal cases. Though the contributions of neurobiological research to forensic technology remain largely hypothetical, the evidences appear promising and further research is both feasible and warranted. The brain based lie detection may veritably give solution to many complicated investigation. This paper explores the evolvement of lie detection technology, their working principles, the latest development, and the prospect of their application in forensic science.","PeriodicalId":160330,"journal":{"name":"2015 Recent and Emerging trends in Computer and Computational Sciences (RETCOMP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125680261","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 : 2015-04-23DOI: 10.1109/RETCOMP.2015.7090797
M. K. Goel
Brain Computer Interface (BCI) aims at providing an alternate means of communication and control to people with severe cognitive or sensory-motor disabilities. These systems are based on the single trial recognition of different mental states or tasks from the brain activity. This paper discusses the major components involved in developing a Brain Computer Interface system which includes the modality to obtain brain signals and its related processing methods.
{"title":"An overview of brain computer interface","authors":"M. K. Goel","doi":"10.1109/RETCOMP.2015.7090797","DOIUrl":"https://doi.org/10.1109/RETCOMP.2015.7090797","url":null,"abstract":"Brain Computer Interface (BCI) aims at providing an alternate means of communication and control to people with severe cognitive or sensory-motor disabilities. These systems are based on the single trial recognition of different mental states or tasks from the brain activity. This paper discusses the major components involved in developing a Brain Computer Interface system which includes the modality to obtain brain signals and its related processing methods.","PeriodicalId":160330,"journal":{"name":"2015 Recent and Emerging trends in Computer and Computational Sciences (RETCOMP)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124704771","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：