The project is based on the development of state-of-the-art large vocabulary continuous speech recognition (LVCSR) system for the Malayalam language. Problems of existing speech recognition are lack of accuracy and misinterpretation, time cost and productivity, accents and speech recognition, background noise interference. The simulation of human intelligence in computers refers to artificial intelligence (AI) which includes Machine Learning, Natural Language Processing, Computer Vision and Robotics. In audio files or video files that are large and have minutes in length, many files have a variety of audio and audio files. In this project, transfer flow technique is used.So the aim of the proposed system of speech recognition is to collect thousands of datasets of each category irrespective of their gender and also they can be of any age group and train them according to their native sequence so as to increase the accuracy level.

Keywords : Artificial Intelligence; Machine Learning; Large Vocabulary Continuous Speech Recognition; Support Vector Machine, Tensor Flow