Abstract
The pace of technological advancement has accelerated significantly. Videos and images have ingrained themselves into daily life. Large amounts of generated video data can be used for real-time analysis. These days, it can be used to improve healthcare and video search. This essay tackles the issue through content analysis. This paper addresses audio feature extraction and multilingual and multicultural considerations. The method in the paper takes videos as a dataset. In this paper, it uses the genism model to extract the matching feature. The similarity table value for different words is between 0.55 to 0.77. The score graph is between 0.4 to 0.8.