This document describes a project to build a speech search engine that can search speeches and lectures by their content. The system will perform noise analysis to reduce noise in audio files. It will use speech recognition to convert speeches to text format and store them in a database along with the audio files. A search engine will then allow users to search the database by content and retrieve relevant audio results. The objectives are to develop noise filtering, a speech recognition system for converting speeches to text, an implementation of databases to store speech data and texts, and a search engine to search database content. This will allow efficient searching of speeches and lectures by textual content.