Speech Recognition and Graph Transformer Nets

This lecture provides an introduction to the problem of speech recognition using neural models, emphasizing the CTC loss for training and inference when input and output sequences are of different lengths. It also covers the concept of beam search for use during inference, and how that procedure may be modeled at training time using a Graph Transformer Network. It is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Modules 1 - 5 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.