Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR

Traditional approach in artificial intelligence (AI) have been solving the problem that is difficult for human but relatively easy for computer if it could be formulated as mathematical rules or formal languages. However, their symbol, rule-based approach failed in the problem where human being solves intuitively like image recognition, natural language understanding and speech recognition. Therefore the machine learning, which is subfield of AI, have tackled this intuitive problems by making the computer learn from data automatically instead of human efforts of extracting complicated rules. Especially the deep learning which is a particular kind of machine learning as well as central theme of this thesis, have shown great popularity and usefulness recently. It has been known that the powerful computer, large dataset and algorithmic improvement have made recent success of the deep learning. And this factors have enabled recent research to train deeper network achieving significant performance improvement. Those current research trends motivated me to quest deeper architecture for the end-to-end speech recognition. In this thesis, I experimentally showed that the proposed deep neural network achieves state-of-the-art results on ‘TIMIT’ speech recognition benchmark dataset. Specifically, the convolutional attention-based sequence-tosequence model which has the deep stacked convolutional layers in the attention-based seq2seq framework achieved 15.8% phoneme error rate.