Time filter

Source Type

Holambe R.S.,Shri Guru Gobind Singhji Institute of Engineering and Technology | Basu T.K.,Institute of Technology and Marine Engineering
Advances in Intelligent and Soft Computing | Year: 2012

The study of text-independent speaker identification in emotional environments is presented in this paper. The study includes identifying the speaker using speech samples in five basic emotions viz. anger, happiness, sadness, disgust, and fear. The work presented compares the performance of four feature sets: Mel frequency cepstral coefficients (MFCC), Line spectral frequencies (LSF), Teager energy based mel cepstral coefficients (TMFCC) and Temporal energy of subband cepstral coefficients (TESBCC). Next, the performance of the speaker identification is studied with combination of two features MFCC-LSF and TESBCC-LSF. A novel classifier fusion method is proposed and its performance is compared with that of the individual classifiers. The database containing speech utterances recorded in the five basic emotions from thirty four speakers in one of the Indian languages (Marathi) is used for experimentation. Gaussian mixture model is used for classification. Fusion of classifiers enhances the speaker identification accuracy in both emotional and neutral environments. © 2012 Springer-Verlag GmbH Berlin Heidelberg.

Holambe R.S.,Shri Guru Gobind Singhji Institute of Engineering and Technology | Basu T.K.,Institute of Technology and Marine Engineering
Proceedings - 5th International Conference on Computational Intelligence and Communication Networks, CICN 2013 | Year: 2013

This paper describes the implementation of unsupervised speaker segmentation and clustering system. Main objective of the work presented in this paper is to study the performance of speaker diarization system using a new feature-set called Temporal Energy of Subband Cepstral Coefficients (TESBCC) and Pitch based features. The system first classifies the audio signal into speech and nonspeech signal using average zero crossing rate (ZCR), followed by a gender clssifier stage. Speaker change is first roughly detected using Hotelling T2 distance metric and then the Bayesian information criterion (BIC) is used to validate the potential speaker change point to reduce the false alarm rate. The bottom-up approach is used for speaker clustering. The performance of the speaker segmentation and clustering system using TESBCC is compared with that using MFCC. © 2013 IEEE.

Holambe R.S.,Shri Guru Gobind Singhji Institute of Engineering and Technology | Basu T.K.,Institute of Technology and Marine Engineering
International Conference on Recent Trends in Information Technology, ICRTIT 2011 | Year: 2011

This paper presents the use of fuzzy min-max neural network for the text independent speaker identification. The fuzzy min-max neural network utilizes fuzzy sets as pattern classes. It is a three layer feedforward network that grows adaptively to meet the demands of the problem. The database containing speech utterances recorded from fifty speakers in Marathi language is used for experimentation. Mel frequency cepstral coefficients that represent short time spectrum are used as features for identification. The results obtained with fuzzy min-max neural network are compared with Gaussian mixture model. It is observed that fuzzy neural network outperforms the Gaussian mixture model and attains the identification accuracy of 99.99 % with 15 second speech utterance. © 2011 IEEE.

Bhowal K.,Academy of Technology | Bhattacharyya D.,Institute of Technology and Marine Engineering | Jyoti Pal A.,Heritage Institute of Technology | Kim T.-H.,Hannam University
Telecommunication Systems | Year: 2013

In the current internet community, secure data transfer is limited due to its attack made on data communication. So more robust methods are chosen so that they ensure secured data transfer. One of the solutions which came to the rescue is the audio Steganography. "A GA Based Audio Steganography with enhanced security" is one propose system which is based on audio Steganography and cryptography, ensures secure data transfer between the source and destination. Here we present a novel, principled approach to resolve the remained problems of substitution technique of audio Steganography. We use most powerful encryption algorithm (RSA) to encrypt message in the first level of security, which is very complex to break. In the second level, we use a more powerful GA based LSB (Least Significant Bit) Algorithm to encode the encrypted message into audio data. Here encrypted message bits are embedded into random and higher LSB layers, resulting in increased robustness against noise addition. The robustness specially would be increased against those intentional attacks which try to reveal the hidden message and also some unintentional attacks like noise addition as well. On the other hand, to reduce the distortion, GA operators are used. The basic idea behind this paper is maintained randomness in message bit insertion into audio data for hiding the data from hackers and multi-objective GA is used to reduce distortion. © 2011 Springer Science+Business Media, LLC.

Biswas S.,Institute of Technology and Marine Engineering | Guha D.,University of Calcutta
AEU - International Journal of Electronics and Communications | Year: 2013

A new technique to characterize an isolated defected ground structure (DGS) is explored. The technique is used to optimize the dimensions of a compact partial-ring DGS to suppress mutual coupling between two E-plane coupled cylindrical dielectric resonator antennas. The optimized design is verified experimentally using a set of fabricated prototypes operating in S-band. A suppression up to 6-7 dB, showing good agreement with the predicted values, is experimentally demonstrated. © 2012 Elsevier GmbH. All rights reserved.

Guha D.,University of Calcutta | Biswas S.,Institute of Technology and Marine Engineering
IEEE Antennas and Propagation Society, AP-S International Symposium (Digest) | Year: 2012

Characterization of defected ground structure (DGS) prior to employing for suppressing mutual coupling between two antennas has been explored for the first time. Commercial simulator is used and the technique leads to the physical insight into its operation. Compact open-ring DGS is considered as a sample and experimentally verified. © 2012 IEEE.

Biswas S.,Institute of Technology and Marine Engineering | Guha D.,University of Calcutta
Progress In Electromagnetics Research M | Year: 2013

A recently developed technique to design and model isolated Defected Ground Structure (DGS) has been examined to control coupling between two adjacent elements in a microstrip array. This is the only technique that can handle isolated DGS and in here, this is explored for the first time in microstrip antenna domain. An X-band design is presented. A set of prototypes are used to obtain measured data which are employed to verify the technique experimentally for microstrip array.

Biswas S.,Institute of Technology and Marine Engineering | Guha D.,University of Calcutta | Kumar C.,Communication Systems Group
IEEE Transactions on Antennas and Propagation | Year: 2013

Controlling higher order modes up to third harmonic of the fundamental operating frequency in a microstrip line-fed patch antenna has been successfully demonstrated. Harmonic rejection in the antenna has been achieved at its feed level using highly compact design of defected ground structure (DGS). Rejection characteristics have been improved adding an open stub to the feed line. All possible higher order modes occurring in between the fundamental and the 3rd harmonic have been identified. Relative suppression of radiated fields with and without DGS-control has been quantitatively measured and effective control of harmonics has been experimentally ensured. The area occupied by the proposed DGS has been compared with earlier designs and over 40-90% reduction in size has been documented. © 2013 IEEE.

Das Gupta J.,Institute of Technology and Marine Engineering | Chanda B.,Indian Statistical Institute
Proceedings - 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010 | Year: 2010

Text line segmentation is one of the important steps for offline handwritten text / handwriting recognition. This paper describes a novel method of text line segmentation based on the physical process of writing. The basic concept behind this segmentation method is: two successive handwritten text-line are always non-intersecting. The proof of the theory is explained with a model of pen-tip movement. The line segmentation is done by arranging the centroids of connected components present in the given text document. Experiments show that the proposed method achieves high accuracy for detecting unconstrained text line of handwritten documents. © 2010 IEEE.

Roy B.,Institute of Technology and Marine Engineering
Proceedings - 3rd International Conference on Intelligent Systems Modelling and Simulation, ISMS 2012 | Year: 2012

In this paper we propose a technique for software-implementation of an UART (Universal-Asynchronous- Receive-Transmit) with the goal of getting a customizable UART-core which can be used as a module in implementing a bigger system irrespective of ones choice of implementation platform. Here we have written the core in VHDL (VHSIC hardware description language), implemented using XILINX ISE 10.1 Design suite and tested in SPARTAN-3AN FPGA evaluation kit by interfacing a test circuit with the PC using the RS232 cable. The simulation results as well as the test results are seen to be satisfactory. The area taken and the power consumed are also evaluated. © 2012 IEEE.

Loading Institute of Technology and Marine Engineering collaborators
Loading Institute of Technology and Marine Engineering collaborators