Pub Date : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437908
S. Singhal, R. Dubey
This work presents an automatic speech recognition (ASR) system for connected words. A connected ASR system has been implemented by extending an isolated word recognizer for speaker dependent data. The work has been applied for English as well as Hindi language. The traditional approach of Mel frequency cepsral coefficient (MFCC) is used as features of the speech signal. Hidden markov model (HMM) and dynamic time warping (DTW) are used at back-end for feature mapping of unknown utterances. A database of isolated English/Hindi words is created for training phase while sentences are used for testing phase. The results are expressed in terms of percentage word error rate (WER). The performance of system for two feature extraction techniques (HMM, DTW) is compared.
{"title":"Automatic speech recognition for connected words using DTW/HMM for English/ Hindi languages","authors":"S. Singhal, R. Dubey","doi":"10.1109/CCINTELS.2015.7437908","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437908","url":null,"abstract":"This work presents an automatic speech recognition (ASR) system for connected words. A connected ASR system has been implemented by extending an isolated word recognizer for speaker dependent data. The work has been applied for English as well as Hindi language. The traditional approach of Mel frequency cepsral coefficient (MFCC) is used as features of the speech signal. Hidden markov model (HMM) and dynamic time warping (DTW) are used at back-end for feature mapping of unknown utterances. A database of isolated English/Hindi words is created for training phase while sentences are used for testing phase. The results are expressed in terms of percentage word error rate (WER). The performance of system for two feature extraction techniques (HMM, DTW) is compared.","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130591172","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 : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437942
Vijay Sharma, Gaurav Kr Sharma, Divesh Kumar
A fully dynamic latched comparator has been designed to meet the requirement of high speed and low power consumption. Such comparators are used in high speed data converters. In this work, dynamic comparators are designed in two different technologies and compared on the basis of delay, offset voltage and power consumption. These comparators work on the concept of charge sharing. Main focus is given towards reduction of both propagation delay and the power dissipation, which will be beneficial in improving performance of the comparator. 90nm CMOS technology is used to simulate the design with 1 V supply voltage. Hspice is used for designing and functional verification.
{"title":"A high speed power efficient dynamic comparator designed in 90nm CMOS technology","authors":"Vijay Sharma, Gaurav Kr Sharma, Divesh Kumar","doi":"10.1109/CCINTELS.2015.7437942","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437942","url":null,"abstract":"A fully dynamic latched comparator has been designed to meet the requirement of high speed and low power consumption. Such comparators are used in high speed data converters. In this work, dynamic comparators are designed in two different technologies and compared on the basis of delay, offset voltage and power consumption. These comparators work on the concept of charge sharing. Main focus is given towards reduction of both propagation delay and the power dissipation, which will be beneficial in improving performance of the comparator. 90nm CMOS technology is used to simulate the design with 1 V supply voltage. Hspice is used for designing and functional verification.","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125399102","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 : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437930
Leo Louis, Ashok Kumar
This paper presents a closed loop scan mechanism using a stepper motor based Gimbal Technique. For its control, Arduino microcontroller based drive electronics is developed. This paper proposes a flexible structure for usefulness in various applications like tracking, satellite imaging etc. This paper analyzes the programming and hardware structure for an easy implementation using the Arduino microcontroller. For a bipolar stepper motor drive, the full H-bridge driver based electronics is developed. Motor shaft position is sensed by incremental optical encoder. The proposed module has high accuracy (.06% in scan rate).
{"title":"Implementation of closed loop based scan mechanism","authors":"Leo Louis, Ashok Kumar","doi":"10.1109/CCINTELS.2015.7437930","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437930","url":null,"abstract":"This paper presents a closed loop scan mechanism using a stepper motor based Gimbal Technique. For its control, Arduino microcontroller based drive electronics is developed. This paper proposes a flexible structure for usefulness in various applications like tracking, satellite imaging etc. This paper analyzes the programming and hardware structure for an easy implementation using the Arduino microcontroller. For a bipolar stepper motor drive, the full H-bridge driver based electronics is developed. Motor shaft position is sensed by incremental optical encoder. The proposed module has high accuracy (.06% in scan rate).","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"16 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126491261","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 : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437917
Chanchal Garg, Y. Narayan, L. Mathew
When the upper limb is amputated or lost, a prosthetic device play an important role in rehabilitation. Prosthetics are available in the form of myoelectric devices. These devices work by sensing the Electromyogram (EMG) signals, through electrodes, when the muscles in the upper arm move, this makes an artificial hand to move accordingly. EMG signals cannot be used directly in raw form to control any prosthetic, it needs to be processed before controlling any device. Different techniques are available for processing the EMG signals. Present paper has used the wavelet transform method to obtain the characteristics or features of EMG signals and then fuzzy controller has been applied on those features so that EMG signals can be used to make prosthetic device functional. NI Lab View, an efficient professional mathematical tool, has been used to process the EMG signals. EMG signals are acquired with the help of sensors placed on the skin and Data Acquisition System. Results of the experiment shows that the developed software module is an effective method to process the EMG signals and can be used for prosthetic devices.
{"title":"Development of a software module for feature extraction and classification of EMG signals","authors":"Chanchal Garg, Y. Narayan, L. Mathew","doi":"10.1109/CCINTELS.2015.7437917","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437917","url":null,"abstract":"When the upper limb is amputated or lost, a prosthetic device play an important role in rehabilitation. Prosthetics are available in the form of myoelectric devices. These devices work by sensing the Electromyogram (EMG) signals, through electrodes, when the muscles in the upper arm move, this makes an artificial hand to move accordingly. EMG signals cannot be used directly in raw form to control any prosthetic, it needs to be processed before controlling any device. Different techniques are available for processing the EMG signals. Present paper has used the wavelet transform method to obtain the characteristics or features of EMG signals and then fuzzy controller has been applied on those features so that EMG signals can be used to make prosthetic device functional. NI Lab View, an efficient professional mathematical tool, has been used to process the EMG signals. EMG signals are acquired with the help of sensors placed on the skin and Data Acquisition System. Results of the experiment shows that the developed software module is an effective method to process the EMG signals and can be used for prosthetic devices.","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128497896","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 : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437965
S. Dey, Ritesh Dash, S. Swain
Sustainable and eco-friendly nature of renewable energy resources render them the best alternatives to conventional fossil fuels. The project proposes analysis and study of Photovoltaic-Wind-Fuel Cell hybrid system for distributed generation system for a remote residential load. A fuzzy logic controller is designed to extract maximum power from both solar and wind energies, which deliver maximal power to a fixed voltage DC bus which then supplies the load, while the surplus power is fed to the electrolyzer which generates hydrogen for the fuel cells and the batteries. Simulation results prove the efficacy of the fuzzy logic controller and establish the fact that these renewable resources can be a viable solution to distributed production of electricity for standalone applications at inaccessible remote locations.
{"title":"Fuzzy based optimal load management in standalone hybrid solar PV/Wind/Fuel Cell generation system","authors":"S. Dey, Ritesh Dash, S. Swain","doi":"10.1109/CCINTELS.2015.7437965","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437965","url":null,"abstract":"Sustainable and eco-friendly nature of renewable energy resources render them the best alternatives to conventional fossil fuels. The project proposes analysis and study of Photovoltaic-Wind-Fuel Cell hybrid system for distributed generation system for a remote residential load. A fuzzy logic controller is designed to extract maximum power from both solar and wind energies, which deliver maximal power to a fixed voltage DC bus which then supplies the load, while the surplus power is fed to the electrolyzer which generates hydrogen for the fuel cells and the batteries. Simulation results prove the efficacy of the fuzzy logic controller and establish the fact that these renewable resources can be a viable solution to distributed production of electricity for standalone applications at inaccessible remote locations.","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125877033","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 : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437954
Shahbaaz Ahmad, Mahfooz Rahman, Muneeb H. Khan, M. S. Umar
User interface design is an important component of human-computer interface. User interface continues to evolve and the emphasis is on imparting more control to end-user and at the same time to facilitate ease of use. This paper proposes a framework for design of an adaptive user interface. The adaptive user interface allows automatic generation of elements of the interface such as buttons, text fields, data fields, menus etc. Moreover, it allows sharing of user screen for design of the interface from distributed locations at the same time. Further, in view of growing importance and widespread use of mobile devices, the framework incorporates portability across different platforms including mobile view. An additional feature is the incorporation of an inbuilt database pertinent to the application to allow the user to develop and design the interface quickly and easily. Mandel's Golden rules for interface design remain the backbone of the proposed framework.
{"title":"A novel framework for adaptive user interface","authors":"Shahbaaz Ahmad, Mahfooz Rahman, Muneeb H. Khan, M. S. Umar","doi":"10.1109/CCINTELS.2015.7437954","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437954","url":null,"abstract":"User interface design is an important component of human-computer interface. User interface continues to evolve and the emphasis is on imparting more control to end-user and at the same time to facilitate ease of use. This paper proposes a framework for design of an adaptive user interface. The adaptive user interface allows automatic generation of elements of the interface such as buttons, text fields, data fields, menus etc. Moreover, it allows sharing of user screen for design of the interface from distributed locations at the same time. Further, in view of growing importance and widespread use of mobile devices, the framework incorporates portability across different platforms including mobile view. An additional feature is the incorporation of an inbuilt database pertinent to the application to allow the user to develop and design the interface quickly and easily. Mandel's Golden rules for interface design remain the backbone of the proposed framework.","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115047560","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 : 2015-11-01DOI: 10.1109/CCINTELS.2015.7437913
Mamta Kumari, I. Ali
In the recent years, the trend of speech signal processing becomes one of the most challenging fields. Now a days, several voice based biometry authentication systems are available to comply the requirements of our daily needs. The overall performances of these systems are totally based on the complexity of each part of the algorithm. Voice Activity Detector (VAD) is one of such relevant part. It can be designed in time domain as well as frequency domain. Time domain VAD have low complexity than the frequency domain or, other domain, like, wavelet transform domain based VAD. Normally, VAD is used to remove the silence portions from the speech signal and a suitable VAD must have high speech activity detection rate (HR1) and high non-speech detection rate (HR0). HP1 and HP0 are quantitative measurement of VAD accuracy to enumerate the speech, and silence part correctly from a speech signal. In this paper, we consider only time domain VAD for clean speech but, the existing time domain based VAD algorithms are not suitable to meet both of them simultaneously. Therefore, we design an unsupervised VAD algorithm which has high HR1, as well as, high HR0. The main advantage of unsupervised data segmentation is that no prior threshold information is required. Here, we use K-mean as an unsupervised clustering technique. In this paper, we compare different time domain voice activity detectors with our proposed VAD which we call it KVD (K-mean Voice-activity Detector). The results of that comparison show the highest performance of our proposed VAD.
{"title":"An efficient un-supervised Voice Activity Detector for clean speech","authors":"Mamta Kumari, I. Ali","doi":"10.1109/CCINTELS.2015.7437913","DOIUrl":"https://doi.org/10.1109/CCINTELS.2015.7437913","url":null,"abstract":"In the recent years, the trend of speech signal processing becomes one of the most challenging fields. Now a days, several voice based biometry authentication systems are available to comply the requirements of our daily needs. The overall performances of these systems are totally based on the complexity of each part of the algorithm. Voice Activity Detector (VAD) is one of such relevant part. It can be designed in time domain as well as frequency domain. Time domain VAD have low complexity than the frequency domain or, other domain, like, wavelet transform domain based VAD. Normally, VAD is used to remove the silence portions from the speech signal and a suitable VAD must have high speech activity detection rate (HR1) and high non-speech detection rate (HR0). HP1 and HP0 are quantitative measurement of VAD accuracy to enumerate the speech, and silence part correctly from a speech signal. In this paper, we consider only time domain VAD for clean speech but, the existing time domain based VAD algorithms are not suitable to meet both of them simultaneously. Therefore, we design an unsupervised VAD algorithm which has high HR1, as well as, high HR0. The main advantage of unsupervised data segmentation is that no prior threshold information is required. Here, we use K-mean as an unsupervised clustering technique. In this paper, we compare different time domain voice activity detectors with our proposed VAD which we call it KVD (K-mean Voice-activity Detector). The results of that comparison show the highest performance of our proposed VAD.","PeriodicalId":131816,"journal":{"name":"2015 Communication, Control and Intelligent Systems (CCIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133223472","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：