The profession of maintaining law and order is not an easy task. It is an inherently stressful job. Due to an increase in crime, policeman’s working hours have also increased, resulting in poor psychological health and increased risk of suicide. Hence, we are building software for the detection of stressed and non-stressed speech for policemen. We propose to develop a system for Central Police Research (CPR) using Machine Learning techniques. We are identifying if a person is in a stressed or non-stressed condition using Python language. We are using two techniques Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) to detect stress in speech.
CITATION STYLE
Pathak, B., Gajbhiye, S., Karjole, A., & Pawar, S. (2021). Comparison between CNN and RNN techniques for stress detection using speech. In Lecture Notes in Networks and Systems (Vol. 171, pp. 333–340). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-33-4543-0_36
Mendeley helps you to discover research relevant for your work.