Bhavneesh Sohal ¹, Sandeep Kaur ¹

Affiliations
1 Computer Science and Engineering, Lovely Professional University, Phagwara, IN

Abstract

Speech is one of the most useful and effective communication medium used as the biometric feature of human being. Speech Recognition is considered as important part of various applications for biometric recognition and translation. Speech can be acquired inexpensively using some mic or phone device. But because of different noise factors that can be included during acquisition increases the complexity in recognition process. Because of this, there is the requirement of more effective and reliable approach for speech recognition. In this present work, a statistical analysis based predictive model is defined to improve the speech recognition. The presented work is defined in the form of a layered model. In first layer of this model, the speech signal improvement is done. To achieve this, the Discrete Wavelet Transform (DWT) and spectral subtraction based approach is defined for noise reduction. This layer improves the speech features. In second layer, the Hidden Markov Model (HMM) improved statistical model is defined to generate the speech features. This layer uses the segmented mean value, standard deviation, variation analysis as the statistical features. In final stage, Distance based mapping is applied on all these features collectively to perform the recognition. The work is implemented for Hindi word recognition. The work is implemented in Matlab environment.

Keywords

Discrete Wavelet Transform (DWT), Hidden Markov Model (HMM), Speech Recognition, Spectral Subtraction, Support Vector Machine (SVM).

Full Text

   

Sandeep Kaur ¹, Bhavneesh Sohal ¹

Affiliations
1 Computer Science and Engineering, Lovely Professional University, Jalandhar-Delhi, G.T. Road, National Highway 1,Phagwara - 144411, Punjab, IN

Abstract

Hand gesture technology makes users’ lives simpler, achieving “hands free” interaction through eliminating the need to hold or press the device. Since the need of human computer interaction has increased to a great-extent, such a technique needs to be devised that do not depend on Vision or Wearable sensors approach. This paper is a sincere attempt to recognize gestures using EM field detection approach. This requires only an EM field transmitter and a detector (receiver). The novelty of this approach is, it not only reduces extra cost for wearable or vision based sensors but would also account for a wide range of coverage area. In addition to this, method to recognize gestures through EM Waves with the help of a laser light is also practically implemented. The demonstration of this method is illustrated with the help of Macromedia Flash Player. This theory will certainly reduce the cost factor and add to the simplicity of the current human computer interactions.

Keywords

Detector, Doppler Shift, Electromagnetic, Flux Points, Gesture Recognition, Light Sensor.

Full Text