Rajamanogaran/Speech-and-information-retrival

This project explores the notion of interacting technology in developing conversational agent that supports human computer interaction. The proposed methodology has three main consecutive modules speech recognition, behavior Intelligence, and speech synthesis in an realtime manner. Speech recognition is a pattern recognition task which enables the system to identify text from human speech. Speech synthesis is artificial production of human speech. It converts the retrieved text into corresponding speech. In addition to these three major modules, natural language processing technology is used to extract information from user context and based on context conversational agent will react.

PythonGPL-3.0