Speech data from the operation of a speech recognition application is recorded over the course of one or more language learning sessions. The operation of the speech recognition application during each language learning sessions corresponds to a user speaking, and the speech recognition application generating text data. The text data may a recognition of what the user spoke. The speech data may comprise the text data, and confidence values that are an indication of an accuracy of the recognition. The speech data from each language learning session may be analyzed to determine an overall performance level of the user.