Nilashree S. Wankhede
Nilashree S. Wankhede has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Sushama Wagh
Veermata Jijabai Technological Institute
2 shared publications Aiman Darwajkar
Electronics and Telecommunication, Fr. Conceicao Rodrigues Institute of Technology, Navi Mumbai, India
1 shared publicationK A Divakara
Society of Applied Microwave Electronics and Engineering & Research (SAMEER), Mumbai, India
1 shared publicationRajesh Harsh
Society of Applied Microwave Electronics and Engineering & Research (SAMEER), Mumbai, India
1 shared publication
Latest Publications
- 25 January 2025
- Published by Springer Nature
- p. 365-378
Augmenting Reliability in Speaker Recognition Systems Through Low Density Parity Check Codes
- 25 January 2025
- Published by Springer Nature
- p. 365-378
Augmenting Reliability in Speaker Recognition Systems Through Low Density Parity Check Codes
- Open Access
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 133921-133930
Enhancing Biometric Speaker Recognition Through MFCC Feature Extraction and Polar Codes for Remote Application
While extensive research has been conducted in the field of biometrics, particularly in face and fingerprint recognition, remote speaker recognition has yet to gain global acceptance due to challenges related to accuracy and data integrity. Previous studies in speaker recognition have explored techniques such as Mel Frequency Cepstral Coefficients (MFCC) and Convolutional Neural Networks (CNN), yielding accuracy rates of 90.4% and 92.8%, respectively over a fixed and small database but on a standalone system. To address the data integrity and accuracy issues for enhancement in remote speaker recognition, a novel approach is proposed in this paper. Initially, remote speaker recognition is implemented using a client-server setup, but the presence of channel noise hindered any noticeable improvement in accuracy compared to existing methods. The new approach involves extracting MFCC parameters from voice samples and subsequently applying polar error-correcting coding techniques for storage as well as transmission to achieve fidelity. Using a code rate of ½ and a block length of 1024 bits, the transmission of polar-coded MFCC features over a noisy channel yielded a lower bit error rate when coupled with successive list decoding. Simulation results demonstrate a reduction in bit error rate, resulting in an accuracy of 95.2% in the implemented remote speaker recognition system. This represents a significant 5% improvement over the existing standalone system that uses MFCC alone and a 2.5% enhancement over the combination of MFCC and CNN. These findings highlight that the Polar codes can be effectively utilized in speaker recognition systems to enhance their robustness and reliability, especially in scenarios with noisy channels or challenging conditions.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 133921-133930
Open AccessEnhancing Biometric Speaker Recognition Through MFCC Feature Extraction and Polar Codes for Remote Application
While extensive research has been conducted in the field of biometrics, particularly in face and fingerprint recognition, remote speaker recognition has yet to gain global acceptance due to challenges related to accuracy and data integrity. Previous studies in speaker recognition have explored techniques such as Mel Frequency Cepstral Coefficients (MFCC) and Convolutional Neural Networks (CNN), yielding accuracy rates of 90.4% and 92.8%, respectively over a fixed and small database but on a standalone system. To address the data integrity and accuracy issues for enhancement in remote speaker recognition, a novel approach is proposed in this paper. Initially, remote speaker recognition is implemented using a client-server setup, but the presence of channel noise hindered any noticeable improvement in accuracy compared to existing methods. The new approach involves extracting MFCC parameters from voice samples and subsequently applying polar error-correcting coding techniques for storage as well as transmission to achieve fidelity. Using a code rate of ½ and a block length of 1024 bits, the transmission of polar-coded MFCC features over a noisy channel yielded a lower bit error rate when coupled with successive list decoding. Simulation results demonstrate a reduction in bit error rate, resulting in an accuracy of 95.2% in the implemented remote speaker recognition system. This represents a significant 5% improvement over the existing standalone system that uses MFCC alone and a 2.5% enhancement over the combination of MFCC and CNN. These findings highlight that the Polar codes can be effectively utilized in speaker recognition systems to enhance their robustness and reliability, especially in scenarios with noisy channels or challenging conditions.
- 29 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Non-Iterative and Fast In-Vivo Gradient Shimming for Magnetic Resonance Imaging
Magnetic Resonance Imaging techniques such as spectroscopic and echo-planar imaging require a highly uniform main magnetic field, B 0 for achieving acceptable diagnostic image quality. In this work a patient-specific, non-iterating and fast gradient shimming method for applying field correction in the imaging plane is described. It requires two gradient-echo images acquired at readout time difference which is a multiple of the fat-water separation frequency of the scanner for 1H protons. A simple phase unwrapping method is applied on the computed B 0 field map to correct for the inherent modulo $2\pi$ phase wrappings. The three linear terms in the orthogonal basis function expansion of the field map are used for estimating the linear shim. Field correction terms are estimated via a magnitude image weighted least squares method. The technique is suitable for linear field shimming of diametric spherical volume centered at the magnet isocenter and could be incorporated into scanners that do not have shimming system.- 29 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Non-Iterative and Fast In-Vivo Gradient Shimming for Magnetic Resonance Imaging
Magnetic Resonance Imaging techniques such as spectroscopic and echo-planar imaging require a highly uniform main magnetic field, B 0 for achieving acceptable diagnostic image quality. In this work a patient-specific, non-iterating and fast gradient shimming method for applying field correction in the imaging plane is described. It requires two gradient-echo images acquired at readout time difference which is a multiple of the fat-water separation frequency of the scanner for 1H protons. A simple phase unwrapping method is applied on the computed B 0 field map to correct for the inherent modulo $2\pi$ phase wrappings. The three linear terms in the orthogonal basis function expansion of the field map are used for estimating the linear shim. Field correction terms are estimated via a magnitude image weighted least squares method. The technique is suitable for linear field shimming of diametric spherical volume centered at the magnet isocenter and could be incorporated into scanners that do not have shimming system.