Audiovisual parsing and augmentation of lecture material – we jointly parse the video and audio. We parse the input video stream to all its unique components and combine it with voice and audio input to index and augment the content / learning experience to produce the desired results.
We build a knowledge Eco-system from all data sources. The transcript from audio, video as well as additional references. In addition to the knowledge available through the provided material we also enrich the knowledge graph with internet search. We then build a reasoning chain on top to make the knowledge indexable and searchable.