Object to Speech Conversion Using YOLO V8
摘要
Object to Speech conversion is very helpful application for the people who are visually impaired. Since this application is capable to giving the audio output, blind people will be easily coming to know what object is there in front of them by listening the speech of computer. This system is able to do the video analysis and image understanding also. There are many approaches which manipulate the images and videos but with the different approaches and same aims. Few AI algorithms like YOLOv8 and TTS are used here to achieve this system. YOLOv8 is used for text conversion and TTS is for speech conversion. A COCO dataset of Microsoft is also used as the trained data.