In this paper, the speech signal is enhanced from the noisy speech signal using the proposed Least Mean Square (LMS) adaptive noise reduction algorithm. In this, the speech signal is enhanced by varying the step size as the function of the input signal. Objective and subjective measures are made under various noises for the proposed and existing algorithms. From the experimental results, it is seen that the proposed LMS adaptive noise reduction algorithm reduces Mean square Error (MSE) as compared to the earlier method under various noise conditions with different input SNR levels. In addition, the proposed spectral subtraction method improves the Peak Signal to Noise Ratio (PSNR) as compared to that of various existing LMS adaptive noise reduction algorithms. From these experimental results, it is observed that the proposed LMS adaptive noise reduction algorithm reduces the speech distortion and residual noise as compared to existing methods.

Speech is one of the most promising models through which various human emotions such as happiness, anger, sadness, and normal state can be determined, apart from facial expressions. Researchers have proved that acoustic parameters of a speech signal such as energy, pitch, Mel frequency Cepstral Coefficient (MFCC) are vital in determining the emotion state of a person. There is an increasing need for a new Feature selection method, to increase the processing rate and recognition accuracy of the classifier, by selecting the discriminative features. This study investigates the various feature selection algorithms, used for selecting the optimal features from speech vectors which are extracted using MFCC. The feature selected is then used in the modeling stage.

No abstract

No abstract

The principle of industrial machine monitoring and vehicle camera transmission system are focusing on this paper. Video compression is widely used in many industrial applications like continuous monitoring of machines which consumes more storage by capturing every motion detection in machine, hence video coding is highly recommended for video compression without any loss in the actual video. By using wavelet transform delivers the superior localization both in frequency and time domain and its results showcases the better performance while comparing with discrete cosine transform. A comparative analysis has been carried on Video compression using Haar and orthogonal (Daubechies) wavelet. Duplicate coefficients of discrete wavelet transform is reduced by using quantization technique. It aims to attain minimum error while preserving the high peak signal to noise ratio and image quality in the acceptable range. Using PSNR as measure of quality, this paper shows that Daubechies wavelet provides the better quality of video compared to Haar wavelet. Evaluation of performance is depends upon on compression ratio, PSNR, MSE, and SSIM.