Knee osteoarthritis is a significant global health concern, 7% of the global population is affected with osteoarthritis problem. Early diagnosis and regular monitoring of knee joint healthcare is crucial to avoid surgeries. Vibroarthrography (VAG) signal records the vibration or acoustic signal of human knee joint while the movement of leg. VAG signal denoising is done by using Variational Mode Decomposition (VMD). This work investigates the effectiveness of VMD in separating a signal into its intrinsic components, followed by the identification and removal of noise-dominated modes. Signal characteristics have been identified using time-domain features, scalograms and spectrograms from the decomposed modes. Machine learning classifiers are then utilized to categorize these signals. Our results indicate that the ensemble voting classifier and AdaBoost achieved an accuracy of 93% in distinguishing between normal and abnormal VAG signals for knee joint healthcare.

In this paper, a Speech Emotion Recognition (SER) system is proposed using the feature combination of Teager Energy Operator (TEO) and Linear Prediction Coefficient (LPC) features as T-LPC feature extraction. The stressed speech signals which were not accurately recognized in the previous SER systems were recognized using the proposed methods. Gaussian Mixture Model (GMM) classifier is used to categorize the emotions of EMO-DB database in this analysis. The Stressed Speech Emotion Recognition (SSER) proposed using the T-LPC feature extraction technique acquired better performance compared to the existing Pitch, LPC, and LPC + Pitch feature based recognition systems. This proposed emotion recognition system can be used to motivate the students by finding their emotional state providing better accuracy compared to the existing ones.

In this paper, a subspace speech enhancement method handling the case of colored noise using oblique projection in the cepstral domain is proposed. Perceptual features and variance normalization are used to reduce the residual noise and improve the intelligibility of the output speech. Initially, the additive noise present in the noisy speech is removed by removing the orthogonal noise subspace from the noisy speech subspace to obtain the speech subspace. Then, the oblique projection of the noise subspace on the speech subspace along the additive noise subspace is used to determine the colored noise that remains. Colored noise removal is performed by power spectral subtraction in the cepstral domain. The spectral domain constrained estimator that incorporates the combined masking property of the human auditory system is employed to estimate the clean speech signal using the variance of the colored noise. To avoid the occurrence of any abrupt spikes in the output, variance normalization is performed by adaptively changing the control parameter of the estimator's gain matrix. The spectrograms, the objective measures and the subjective intelligibility test show the superior performance of the proposed method over the other existing speech enhancement methods.