RESEARCH AND BUILD A MODEL SPEECH EMOTION RECOGNITION

Abstract

In the context of digital technology, big data, it requires people to process a lot
of information at the same time. The problem is that companies need to classify
and evaluate customer feedback through voice messages, voice recognition for
chatbots to have the next processing direction, and identify emotions through
voice. speaking for the human robots, in order to handle the feedback directions.
The article proposes a plan to create a model to identify and classify this data. The
content of the paper focuses on the application of machine learning in data
classification and using the logistic regressiong problem to set up the Model, set the
Loss Function, optimize the loss function and predict the model.