Emotion recognition is a piece of software which can identify the emotions of the user. This can be implemented using multiple machine learning algorithms. In this project, we have used Deep Neural Network to predict the emotions. Through this project we present a multimodal approach for the recognition of seven emotions. Our approach integrates information from facial expressions and speech. The main idea of this project is to make the machines intelligent enough for the interaction of users, for these machines should be able to understand the emotion of humans while interacting with them. Face and speech play critical role in emotion recognition. In terms of machines and robots who observe through images and different kind of sensors, detecting emotion through face and speech can play important role and will make machine more socially intelligent and acceptable There are many applications for emotion recognition such as speech emotion recognition system can be used in -Aircraft cockpits to provide analysis of Psychological state of pilot to avoid accidents. It also utilizes to recognize stress in speech for better performance, lie detection etc. The applications for emotion recognition from face includes - the online sales system will automatically tailor the services they offer to the customer based on the facial reactions. While browsing the contents of an e-shop, the computer automatically scans the facial expression and based on that, the system can suggest further product that may be of interest to the customer