naveen dubey - Academia.edu (original) (raw)
Papers by naveen dubey
International Journal of Computer Trends and Technology, Oct 25, 2015
Blind Audio Source Separation is a technique to separate out audio signal from various sources re... more Blind Audio Source Separation is a technique to separate out audio signal from various sources recorded by number of microphones placed at different positions. ICA is dominant technique to separate independent components of signals from mixture. Inequality based divergence measure is used to develop a contrast function for source separation using ICA.This work addresses various divergence measures and performance of inequality based divergence measure. Experimental result reflects that Jenson Inequality based convex divergence measure gives better performance than other divergence measures such as Euclidian, Kullback leibler, Cauchy-Schwartz etc. Convex divergence measure for α=-1 gives 20-25% better and faster convergence than other and can be adopted for audio source separation by incorporating Independent component analysis..
This paper introduced comparative analysis of blind audio source separation techniques in time do... more This paper introduced comparative analysis of blind audio source separation techniques in time domain, frequency domain. In time domain analysis modified convex divergence method and ICA decomposition techniques are considered and in frequency domain Inter-frequency Correlation with Microphone Diversity techniques are considered. To perform this analysis a critically determined system consists of three audio sources and three microphones are considered. Frequency domain analysis can be implemented for over determined mixture also, in that it extracts principle component to form a determined mixture. Simulations are performed on a closed room recording samples and convergence speed and complexity is compared. Result reflects that divergence based ICA overshadows the other competitors in terms of convergence speed and proved as a better audio source separation technique in blind scenario.
Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on ... more Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on complete decomposition or based on complete decomposition. Partial decomposition of observation space leads to additional computational complexity and burden, to minimize resource requirement complete decomposition technique is preferred. In this script an optimized divergence based ICA technique is proposed to perform ICA decomposition. After decomposition components having similar behaviour are grouped in form of clusters and source signals are reconstructed. The authors implemented complete decomposition for BASS using ICA methods and K-mean cluster technique is introduced. For performance evaluation a three source and three microphones combination is used and result advocates complete decomposition by optimized ICA is a better option than other methods in competition for audio source separation in blind scenario.
In this paper , the threshold variation due to modification in doping profile and random trap pos... more In this paper , the threshold variation due to modification in doping profile and random trap position has been analysed. This analysis has been done on N-MOS with 40 nm channel length and 32 nm effective channel length . The trap position is changing from drain end to source end and results were observed for different doping profiles .The results shows that the fluctuation in VThreshold is not consistent and the standard deviation are dependent on the trap position as well as on the nature of doping profile. As the Gaussian doping profile shows less fluctuation in comparison of Error function doping profile. The threshold voltage standard deviation is highly correlated when the trap is located in between the centre.
The audio source separation in blind mixing environment plays a key role in various application s... more The audio source separation in blind mixing environment plays a key role in various application such as humanoids, human machine interaction etc . In this work various quality measure have been discussed and a separation quality evaluation method BSS_Eval has been demonstrated. This work also includes separation quality analysis of blind mixture in subGaussian and super-Gaussian mixing scenario. Experimental result reflects that all separated signals having positive kurtosis, which ensures super-Gaussian nature of separated components and SIR value of separated independent components is 19.64% higher for super-Gaussian mixing in comparison of sub-Gaussian
Taking assumption the hidden sources are statistically independent, Independent component analysi... more Taking assumption the hidden sources are statistically independent, Independent component analysis technique separates these sources from a linear mixture of audio signals, communication signals generated by equally spaced independent audio sources. Since, in Audio applications source exhibit non dependence. Mutual information minimization corresponds to minimization of entropy, that ensures quality of separation and exploits non-Gaussianity, noncircularity and sample dependence simultaneously. In this paper these properties are exploited with the help of Cramer-Rao lower bound, modified convex divergence based ICA, Fast ICA and JADE. The performance of these techniques are examined with the help of a number of example and a comparative analysis presented in term of failure percentage and average CPU time taken for execution. Keywords— Independent Component Analysis, Blind Source Separation, Convex Divergence, Independence, non-Gaussianity,.
Separation Science Plus
Interconversion or back conversion from a parent compound to its metabolites or vice versa has ne... more Interconversion or back conversion from a parent compound to its metabolites or vice versa has never been clearly understood and established by using mass spectrometry. This makes it a daunting challenge for which the technique of liquid chromatography with tandem mass spectrometry supports it while an other hyphenated technique liquid chromatography with ultraviolet detection employed for investigation lacks it. Herein, a selective and sensitive liquid chromatography with tandem mass spectrometry method for the simultaneous determination of Clomipramine and its active metabolite N-Desmethyl Clomipramine in human plasma was developed and validated. A suitable method for investigating interconversion between Clomipramine and its active metabolite to each other by two analytical tools was achieved and its impact on a bioequivalence study was evaluated. Stable labeled internal standards i.e. Clomipramine D3 and N-Desmethyl Clomipramine D3 were used as internal standard to track and compensate the parent compound during processing and extraction from plasma. The method involves a rapid liquid-liquid extraction (followed by flash freezing under dry ice bath) from plasma followed by reversed gradient chromatography condition and mass spectrometry detection. The mean recovery for Clomipramine and N-Desmethyl Clomipramine were 62.1 and 63.2%, respectively.
2015 4th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions), 2015
Audio Source separation techniques are used for better reception of sound and speech signals. Wie... more Audio Source separation techniques are used for better reception of sound and speech signals. Wiener filtering tool is best and one of the principally used method in separation of the audio signal from mixture of source signals. As the STFT utilizes short-duration stationarity in time frequency domain, we use Wiener filtering mask which does not depends on the consistency of the output for the voice gram and is different from the STFT in time-frequency domain. Short-time Fourier transform (STFT) in time-frequency domain is used if processing is done on audio signals. In this paper a technique for blind audio source separation using Wiener filtering algorithm is presented and result reflects that it serves good quality of separation in comparison of classical ICA algorithms like fast ICA, JADE. So it gives the SIR value 6.68% and 39.22% higher than that of fast ICA and JADE respectively.
International Journal of Computer Applications, 2015
Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on ... more Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on complete decomposition or based on complete decomposition. Partial decomposition of observation space leads to additional computational complexity and burden, to minimize resource requirement complete decomposition technique is preferred. In this script an optimized divergence based ICA technique is proposed to perform ICA decomposition. After decomposition components having similar behaviour are grouped in form of clusters and source signals are reconstructed. The authors implemented complete decomposition for BASS using ICA methods and K-mean cluster technique is introduced. For performance evaluation a three source and three microphones combination is used and result advocates complete decomposition by optimized ICA is a better option than other methods in competition for audio source separation in blind scenario.
2015 1st International Conference on Next Generation Computing Technologies (NGCT), 2015
Blind audio source separation is a promising area for various applications like humanoids, human ... more Blind audio source separation is a promising area for various applications like humanoids, human machine inter- action or adverse control mechanism, etc. ICA is a predominant approach for source separation in blind scenario. There are various versions of ICA to solve this purpose like Fast ICA, JADE, and C-ICA. The convergence speed and quality of separation is an issue. In this work a weight initialization approach is proposed for optimizing the convergence speed and experimental results reflects up to 28.57% that the proposed weight initialized ICA gives better convergence speed in comparison of Fast ICA. Here a critically determined ideal mixing system is considered where no noise component is taken into account.
Journal of Electrical and Electronics Engineering
Audio processing is an area where signal separation is considered as a fascinating works, potenti... more Audio processing is an area where signal separation is considered as a fascinating works, potentially offering a vivid range of new scope and experience in professional and personal context. The objective of Blind Audio Source Separation is to separate audio signals from multiple independent sources in an unknown mixing environment. This paper addresses the key challenges in BASS and unsupervised approaches to counter these challenges. Comparative performance analysis of Fast-ICA algorithm and Convex Divergence ICA for Blind Source Separation is presented with the help of experimental result. Result reflects Convex Divergence ICA with α=-1 gives more accurate estimate in comparison of Fast ICA. In this paper algorithms are considered for ideal mixing situation where no noise component taken in to account.
In this paper , the threshold variation due to modification in doping profile and random trap pos... more In this paper , the threshold variation due to modification in doping profile and random trap position has been analysed. This analysis has been done on N-MOS with 40 nm channel length and 32 nm effective channel length . The trap position is changing from drain end to source end and results were observed for different doping profiles .The results shows that the fluctuation in V Threshold is not consistent and the standard deviation are dependent on the trap position as well as on the nature of doping profile. As the Gaussian doping profile shows less fluctuation in comparison of Error function doping profile. The threshold voltage standard deviation is highly correlated when the trap is located in between the centre.
2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), 2014
Acquisition is an essential building block in almost any real life data processing. In acquisitio... more Acquisition is an essential building block in almost any real life data processing. In acquisition it is key target to keep aliasing low often dictates the use of a complex analog anti-aliasing filter. In case of multichannel system, each channel must be fitted with a separate anti-aliasing filter as such filter cannot be multiplexed but this exercise becomes expensive. In this paper the cost optimized structure for multiple channel data acquisition system is proposed, the cost optimization achieved by using multistage decimation. The MATLAB simulation has been used to evaluate proposed model and in result cost reduced by 53.27% when (M=16*2) has been used instead of M=32. The cost has been further reduced by 69% for combination of M=(8*4), Key targets are filter length reduction and aliasing. Finite-impulse-response (FIR) has been used for implementation of idea.
International Journal of Information Technology and Computer Science, 2016
Separating audio sources from a convolutive mixture of signals from various independent sources i... more Separating audio sources from a convolutive mixture of signals from various independent sources is a very fascinating area in personal and professional context. The task of source separation becomes trickier when there is no idea about mixing environment and can be termed as blind audio source separation (BASS). Mixing scenario becomes more complicated when there is a difference between number of audio sources and number of recording microphones, under determined and over determined mixing. The main challenge in BASS is quality of separation and separation speed and the convergence speed gets compromised when separation techniques focused on quality of separation. This work proposed divergence algorithm designed for faster convergence speed along with good quality of separation. Experiments are performed for critically determined audio recording, where number of audio sources is equal to number of microphones and no noise component is taken into consideration. The result advocates that the modified convex divergence algorithm enhance the convergence speed by 20-22% and good quality of separation than conventional convex divergence ICA, Fast ICA, JADE.
International Journal of Computer Trends and Technology, Oct 25, 2015
Blind Audio Source Separation is a technique to separate out audio signal from various sources re... more Blind Audio Source Separation is a technique to separate out audio signal from various sources recorded by number of microphones placed at different positions. ICA is dominant technique to separate independent components of signals from mixture. Inequality based divergence measure is used to develop a contrast function for source separation using ICA.This work addresses various divergence measures and performance of inequality based divergence measure. Experimental result reflects that Jenson Inequality based convex divergence measure gives better performance than other divergence measures such as Euclidian, Kullback leibler, Cauchy-Schwartz etc. Convex divergence measure for α=-1 gives 20-25% better and faster convergence than other and can be adopted for audio source separation by incorporating Independent component analysis..
This paper introduced comparative analysis of blind audio source separation techniques in time do... more This paper introduced comparative analysis of blind audio source separation techniques in time domain, frequency domain. In time domain analysis modified convex divergence method and ICA decomposition techniques are considered and in frequency domain Inter-frequency Correlation with Microphone Diversity techniques are considered. To perform this analysis a critically determined system consists of three audio sources and three microphones are considered. Frequency domain analysis can be implemented for over determined mixture also, in that it extracts principle component to form a determined mixture. Simulations are performed on a closed room recording samples and convergence speed and complexity is compared. Result reflects that divergence based ICA overshadows the other competitors in terms of convergence speed and proved as a better audio source separation technique in blind scenario.
Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on ... more Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on complete decomposition or based on complete decomposition. Partial decomposition of observation space leads to additional computational complexity and burden, to minimize resource requirement complete decomposition technique is preferred. In this script an optimized divergence based ICA technique is proposed to perform ICA decomposition. After decomposition components having similar behaviour are grouped in form of clusters and source signals are reconstructed. The authors implemented complete decomposition for BASS using ICA methods and K-mean cluster technique is introduced. For performance evaluation a three source and three microphones combination is used and result advocates complete decomposition by optimized ICA is a better option than other methods in competition for audio source separation in blind scenario.
In this paper , the threshold variation due to modification in doping profile and random trap pos... more In this paper , the threshold variation due to modification in doping profile and random trap position has been analysed. This analysis has been done on N-MOS with 40 nm channel length and 32 nm effective channel length . The trap position is changing from drain end to source end and results were observed for different doping profiles .The results shows that the fluctuation in VThreshold is not consistent and the standard deviation are dependent on the trap position as well as on the nature of doping profile. As the Gaussian doping profile shows less fluctuation in comparison of Error function doping profile. The threshold voltage standard deviation is highly correlated when the trap is located in between the centre.
The audio source separation in blind mixing environment plays a key role in various application s... more The audio source separation in blind mixing environment plays a key role in various application such as humanoids, human machine interaction etc . In this work various quality measure have been discussed and a separation quality evaluation method BSS_Eval has been demonstrated. This work also includes separation quality analysis of blind mixture in subGaussian and super-Gaussian mixing scenario. Experimental result reflects that all separated signals having positive kurtosis, which ensures super-Gaussian nature of separated components and SIR value of separated independent components is 19.64% higher for super-Gaussian mixing in comparison of sub-Gaussian
Taking assumption the hidden sources are statistically independent, Independent component analysi... more Taking assumption the hidden sources are statistically independent, Independent component analysis technique separates these sources from a linear mixture of audio signals, communication signals generated by equally spaced independent audio sources. Since, in Audio applications source exhibit non dependence. Mutual information minimization corresponds to minimization of entropy, that ensures quality of separation and exploits non-Gaussianity, noncircularity and sample dependence simultaneously. In this paper these properties are exploited with the help of Cramer-Rao lower bound, modified convex divergence based ICA, Fast ICA and JADE. The performance of these techniques are examined with the help of a number of example and a comparative analysis presented in term of failure percentage and average CPU time taken for execution. Keywords— Independent Component Analysis, Blind Source Separation, Convex Divergence, Independence, non-Gaussianity,.
Separation Science Plus
Interconversion or back conversion from a parent compound to its metabolites or vice versa has ne... more Interconversion or back conversion from a parent compound to its metabolites or vice versa has never been clearly understood and established by using mass spectrometry. This makes it a daunting challenge for which the technique of liquid chromatography with tandem mass spectrometry supports it while an other hyphenated technique liquid chromatography with ultraviolet detection employed for investigation lacks it. Herein, a selective and sensitive liquid chromatography with tandem mass spectrometry method for the simultaneous determination of Clomipramine and its active metabolite N-Desmethyl Clomipramine in human plasma was developed and validated. A suitable method for investigating interconversion between Clomipramine and its active metabolite to each other by two analytical tools was achieved and its impact on a bioequivalence study was evaluated. Stable labeled internal standards i.e. Clomipramine D3 and N-Desmethyl Clomipramine D3 were used as internal standard to track and compensate the parent compound during processing and extraction from plasma. The method involves a rapid liquid-liquid extraction (followed by flash freezing under dry ice bath) from plasma followed by reversed gradient chromatography condition and mass spectrometry detection. The mean recovery for Clomipramine and N-Desmethyl Clomipramine were 62.1 and 63.2%, respectively.
2015 4th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions), 2015
Audio Source separation techniques are used for better reception of sound and speech signals. Wie... more Audio Source separation techniques are used for better reception of sound and speech signals. Wiener filtering tool is best and one of the principally used method in separation of the audio signal from mixture of source signals. As the STFT utilizes short-duration stationarity in time frequency domain, we use Wiener filtering mask which does not depends on the consistency of the output for the voice gram and is different from the STFT in time-frequency domain. Short-time Fourier transform (STFT) in time-frequency domain is used if processing is done on audio signals. In this paper a technique for blind audio source separation using Wiener filtering algorithm is presented and result reflects that it serves good quality of separation in comparison of classical ICA algorithms like fast ICA, JADE. So it gives the SIR value 6.68% and 39.22% higher than that of fast ICA and JADE respectively.
International Journal of Computer Applications, 2015
Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on ... more Algorithms for Blind Audio Source Separation (BASS) in time domain can be categories as based on complete decomposition or based on complete decomposition. Partial decomposition of observation space leads to additional computational complexity and burden, to minimize resource requirement complete decomposition technique is preferred. In this script an optimized divergence based ICA technique is proposed to perform ICA decomposition. After decomposition components having similar behaviour are grouped in form of clusters and source signals are reconstructed. The authors implemented complete decomposition for BASS using ICA methods and K-mean cluster technique is introduced. For performance evaluation a three source and three microphones combination is used and result advocates complete decomposition by optimized ICA is a better option than other methods in competition for audio source separation in blind scenario.
2015 1st International Conference on Next Generation Computing Technologies (NGCT), 2015
Blind audio source separation is a promising area for various applications like humanoids, human ... more Blind audio source separation is a promising area for various applications like humanoids, human machine inter- action or adverse control mechanism, etc. ICA is a predominant approach for source separation in blind scenario. There are various versions of ICA to solve this purpose like Fast ICA, JADE, and C-ICA. The convergence speed and quality of separation is an issue. In this work a weight initialization approach is proposed for optimizing the convergence speed and experimental results reflects up to 28.57% that the proposed weight initialized ICA gives better convergence speed in comparison of Fast ICA. Here a critically determined ideal mixing system is considered where no noise component is taken into account.
Journal of Electrical and Electronics Engineering
Audio processing is an area where signal separation is considered as a fascinating works, potenti... more Audio processing is an area where signal separation is considered as a fascinating works, potentially offering a vivid range of new scope and experience in professional and personal context. The objective of Blind Audio Source Separation is to separate audio signals from multiple independent sources in an unknown mixing environment. This paper addresses the key challenges in BASS and unsupervised approaches to counter these challenges. Comparative performance analysis of Fast-ICA algorithm and Convex Divergence ICA for Blind Source Separation is presented with the help of experimental result. Result reflects Convex Divergence ICA with α=-1 gives more accurate estimate in comparison of Fast ICA. In this paper algorithms are considered for ideal mixing situation where no noise component taken in to account.
In this paper , the threshold variation due to modification in doping profile and random trap pos... more In this paper , the threshold variation due to modification in doping profile and random trap position has been analysed. This analysis has been done on N-MOS with 40 nm channel length and 32 nm effective channel length . The trap position is changing from drain end to source end and results were observed for different doping profiles .The results shows that the fluctuation in V Threshold is not consistent and the standard deviation are dependent on the trap position as well as on the nature of doping profile. As the Gaussian doping profile shows less fluctuation in comparison of Error function doping profile. The threshold voltage standard deviation is highly correlated when the trap is located in between the centre.
2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), 2014
Acquisition is an essential building block in almost any real life data processing. In acquisitio... more Acquisition is an essential building block in almost any real life data processing. In acquisition it is key target to keep aliasing low often dictates the use of a complex analog anti-aliasing filter. In case of multichannel system, each channel must be fitted with a separate anti-aliasing filter as such filter cannot be multiplexed but this exercise becomes expensive. In this paper the cost optimized structure for multiple channel data acquisition system is proposed, the cost optimization achieved by using multistage decimation. The MATLAB simulation has been used to evaluate proposed model and in result cost reduced by 53.27% when (M=16*2) has been used instead of M=32. The cost has been further reduced by 69% for combination of M=(8*4), Key targets are filter length reduction and aliasing. Finite-impulse-response (FIR) has been used for implementation of idea.
International Journal of Information Technology and Computer Science, 2016
Separating audio sources from a convolutive mixture of signals from various independent sources i... more Separating audio sources from a convolutive mixture of signals from various independent sources is a very fascinating area in personal and professional context. The task of source separation becomes trickier when there is no idea about mixing environment and can be termed as blind audio source separation (BASS). Mixing scenario becomes more complicated when there is a difference between number of audio sources and number of recording microphones, under determined and over determined mixing. The main challenge in BASS is quality of separation and separation speed and the convergence speed gets compromised when separation techniques focused on quality of separation. This work proposed divergence algorithm designed for faster convergence speed along with good quality of separation. Experiments are performed for critically determined audio recording, where number of audio sources is equal to number of microphones and no noise component is taken into consideration. The result advocates that the modified convex divergence algorithm enhance the convergence speed by 20-22% and good quality of separation than conventional convex divergence ICA, Fast ICA, JADE.