Human spoken language understanding relies heavily on contextual information. If we consider a single word, the context might simply be the words surrounding it. These words provide important clues for the listener to accurately recognize and understand the word of interest. This word may be hard to recognize because it sounds similar to other words, it is pronounced different from speaker to speaker, or it may be obfuscated by noise. Even when the word is completely unknown to the listener, context may help in deriving its meaning. Thus, training machines to use context in a similar way is an important path towards machines that can mimic the human understanding of spoken language.