Abstract
The main goal of our project is to identify the emotions a speaker evokes when speaking. For example, utterances uttered in states of fear, surprise, excite- ment, anger, or joy are loud and fast and have a large and wide pitch range, whereas utterances uttered in states of depression or fatigue are slow and deep. This is us We use deep learning techniques to build models that can identify human emotions through the analysis of speech and language patterns. The main reason for choosing this project is that speech sentiment analysis has become one of the largest commercialization strategies in which client moods and dispositions play a large role. Therefore, there is an increased demand for products or companies to recognize an individual’s emotions and recommend appropriate products or assist him accordingly. It can also be used to monitor status. More recently, speech recognition and analysis have also been applied to medicine and forensics.
Keywords
)