Abstract- We present a keyword spotting (KWS) system for lecture video that uses deep (CNN) architectur. The CNN architecture enables us to use lecture video speech data that was taken under a diverse condition as a training dataset without any specialized feature. We also employ the language model an word stemming on the resulting transcript to correct misspelling and error automatically. Our model yield and averange accuracy of 69.01% which is 34.53% improvement from the baseline model. We also show that an augmentation of the training dataset improves the model robustnes against the testing dataset