We will build probabilistic and deep learning models, such as hidden Markov models and recurrent neural networks, to teach the computer to do tasks such as speech recognition, machine translation.
Speech_Tagging: In the first project, we will use several techniques, including table lookups, n-grams, and hidden Markov models, to tag parts of speech in sentences, and compare their performance.
Machine_Translation: In the second project, we will build a deep neural network that functions as part of an end-to-end machine translation pipeline.
Speech_Recognizer: In the third project, we will build a deep neural network that functions as part of an end-to-end automatic speech recognition (ASR) pipeline.