Our system allows teachers to create questions for sections they deem important during a lecture. The system automatically summarizes and creates relevant questions based on key words which can be used for quizzes, discussions, or study notes. This system evolves on the study technique of “Active Recall”, where you answer questions while learning to remember and understand topics better.
Machine Learning -- This system was accomplished using the Google Cloud Speech-to-Text for speech recognition and the T5-bas training model for summarization. Pre-trained models seemed the most efficient as we did not possess the amount of data or time to create and train an accurate model ourselves. A similar model based on T5, named End-to-End Sequence-to-Sequence Question Generation was used to produce questions based on created summarizations.
Intuitive User Interface -- To develop this interface, we initially started with Figma. This allowed us to visually depict how our website should look and work along with easily acquiring the CSS. The teacher interface was designed to not take too much attention away from the lecture. Teachers would be able to make a room and give students a code to join. Questions made by from the recordings are automatically uploaded to Google Cloud. These questions would be able to be viewed by students using the student section by joining a room. The questions themselves would be released at the end of a lecture. These rooms would display all the questions generated throughout the lecture.
Backend Design -- The backend of Lecture T-Ai had always been decided to be using Flask and JavaScript to both host a database for login info along with recording and storing audio clips for our ML backend. To create an easy method for creating audio clips which are later broken into chunks for transcription, we used JavaScript. We used JavaScript’s inbuilt media encoder to generate .webm files which would be later converted to the .wav files we would need to process the audio.