Search

This paper focusses on investigation of the effective performance of perceptual based speech features on emotion detection. Mel frequency cepstral coefficients (MFCC's), perceptual linear predictive cepstrum (PLPC), Mel frequency perceptual linear prediction cepstrum (MFPLPC), bark frequency cepstral coefficients (BFCC), revised perceptual linear prediction coefficient's (RPLP) and inverted Mel frequency cepstral coefficients (IMFCC) are the perception features considered. The algorithm using these auditory cues is evaluated with deep neural networks (DNN). The novelty of the work involves analysis of the perceptual features to identify predominant features that contain significant emotional information about the speaker. The validity of the algorithm is analysed on publicly available Berlin database with seven emotions in 1-dimensional space termed categorical and 2-dimensional continuous space consisting of emotions in valence and arousal dimensions. Comparative analysis reveals that considerable improvement in the performance of emotion recognition is obtained using DNN with the identified combination of perceptual features. [ABSTRACT FROM AUTHOR]

This paper investigates the potential of COVID-19 detection using cough, breathing, and voice patterns. Speech-based features, such as MFCC, zero crossing rate, spectral centroid, spectral bandwidth, and chroma STFT are extracted from audio recordings and evaluated for their effectiveness in identifying COVID-19 cases from Coswara dataset. The explainable AI SHAP tool is employed which identified MFCC, zero crossing rate, and spectral bandwidth as the most influential features. Data augmentation techniques like random sampling, SMOTE, Tomek, and Edited Nearest Neighbours (ENN), are applied to improve the performance of various machine learning models used viz. Naive Bayes, K-nearest neighbours, support vector machines, XGBoost, and Random Forest. Selecting the top 20 features achieves an accuracy of 73%, a precision of 74%, a recall of 94%, and an F1-score of 83% using the Random Forest model with the Tomek sampling technique. These findings demonstrate that a carefully selected subset of features can achieve comparable performance to the entire feature set while maintaining a high recall rate. The success of the Tomek undersampling technique highlights the ability of model to handle sparse clinical data and predict COVID-19 and associated diseases using speech-based features. [ABSTRACT FROM AUTHOR]

During recent years, scientists have endeavored to meet the challenging necessities of creating top notch programming applications. Building venture class arrangements like a Big Data Analytics Platform includes testing enormous measures of clinical trial information from different investigations, subjects, and installed gadgets. Handling and putting away terabytes or petabytes of information may take days or weeks to finish. Utilizing an extensive informational collection amid programming advancement and testing, postpones the constant incorporation and conveyance endeavors. A novel method has been proposed to reduce the input data set for such big data applications without compromising on quality of results by creating a smaller representative sample out of given big data datasets and using that representative sample to drive the application further. The proposed approach makes use of Pairwise Test Case Generation methodology to identify he diminished arrangement of datasets ensuring that each pair of input parameters have been enclosed by at least one input data tuple. Although using pairwise methodology might not be exhaustive, but it is found to be very useful because it can significantly reduce the input dataset and can still cover hypothetically difficult relations within different input domain parameters. The paper describes the proposed hybrid pairwise test generation approach based upon Cuckoo Search (CS) and Genetic Algorithms (GA) and applies the approach on big data dataset to come up with representative data sets which are much reduced as compared to original ones. The big data datasets taken as input to prove the effectiveness of proposed approach are the test cases intended to be used for defect finding. The quality of newly generated representative datasets with proposed approach is also evaluated against the original big sized big data datasets. [ABSTRACT FROM AUTHOR]