Identifying the Sound Event Recognition using Machine learning And Artificial Intelligence
The analysis of sound information is extremely useful in a variety of applications such as multimedia information retrieval, audio surveillance, audio tagging, and forensic investigations. The analysis of an audio clip is performed in order to detect sound events. Applications of this technology include security systems, smart vehicle navigation and noise pollution monitoring. Sound Event Recognition (SER) is the focus of this research proposal. As compared to long-duration audio scenes, sound events have a short duration of about 100 to 500 milliseconds. A machine-learning model is being trained and tested in this paper, which can be incorporated in an automated data collection process. In this experiment, Convolutional Neural Network (CNN), Support Vector Machine (SVM), Hidden Markov Model (HMM) and Random Forest were compared.