Intelligently speech recognition and conversion with noise reduction

Speech to Text conversion is an advanced artificial intelligence system where the machine can recognize the user’s voice then, interpreted it into text. The work of the speech recognition process started before the 70s, now, it is more developed and works in a more efficient way, also can handle complex expressions. These systems can help people who want to write convert texts into different languages quickly. Though, existing systems lack more features like multiple languages (9) in a single domain. We have implemented a system that overcomes this problem. Speech recognition and synthesis technology are one of the im-portant and fastest-growing Information technologies. Nowadays, Many applications have many potential benefits in different areas. Among the whole world population, About 25% are suffering from various disabilities; There are many people among them who are blind or cannot able to use their hands perfectly. This system gives them unexpected and evaluated support in this field so that they can write and express information with humans by managing computers, tablets, mobile, or any kind of information through voice input. This project has been planned, designed, and developed using Visual studio with JavaScript and C# programming based on MFCC and HMM.