Using praat to match stimuli5/25/2023 This study examines the contents of calls landed in the emergency response support system (ERSS) during the pandemic. New psychological services must be established as quickly as possible to support the mental healthcare needs of people in this pandemic condition. People are facing unprecedented levels of intense threat, necessitating professional, systematic psychiatric intervention and assistance. The COVID-19 precautions, lockdown, and quarantine implemented throughout the epidemic resulted in a worldwide economic disaster. In all three experiments, the worst results were obtained in tests with the SAVEE database - 20.24%, 18.45% and 22.02%. Tests with the EMO-DB database were successful at 35.76%, 31.75% and 25.49%. Their common feature is that the prediction success was always highest in tests with a test subset of the RAVDESS database, with the best result being obtained using a 1D convolutional network (78.93%). Therefore, 3 experiments with forward, 1 and 2D convolutional neural networks were performed to determine the overall success of the classification. In the current version of the application, the use of Praat has been eliminated and we have developed our solution based on neural networks. In the original application, we have used the Praat program to extract the characteristics. Due to the applied k-NN algorithm, the original solution achieved an overall classification success in the range of 20 to 35%, depending on the used audio sample input data database. The paper deals with the issue of classification of emotional state from speech. In the paper are presented the results of the created application testing and the possibilities of further expansion and improvement of this solution. The paper deals with the user's emotional state classification based on the voice track analysis, it describes its own solution - the measurement and the selection process of appropriate voice characteristics using ANOVA analysis and the use of PRAAT software for many voice aspects analysis and for the implementation of own application to classify the user's emotional state from his/her voice. The goal of adaptive interaction between man and computer is the human needs understanding. One of the interaction possibilities is a voice control which nowadays can‘t be restricted only to direct commands. This development has shown that it is important not only to shift performance and functional boundaries but also to adapt the way human-computer interaction to modern needs. During the last decades the field of IT has seen an incredible and very rapid development.
0 Comments
Leave a Reply. |