Lab 4 — Large Vocabulary Decoding: A Love Story

By far the sexiest piece of software associated with ASR is the large-vocabulary decoder. Since this course is nothing if not about being sexy, this assignment will deal with various aspects of large-vocabulary decoding. In the first portions of this lab, we will investigate the various steps involved in building static decoding graphs as will be needed by our decoder. In the second half of the lab, you will implement most of the interesting parts of a real-time largevocabulary decoder. In particular, you will need to re-implement the Viterbi algorithm from Lab 2, except this time youwill need to worry about memory and speed considerations as well as skip arcs. This will involve implementing token passing and beam pruning, and optionally rank pruning. The goal of this assignment is for you, the student, to gain a better understanding of the various steps involved in constructing a static decoding graph for LVCSR and of the various algorithms used in large-vocabulary decoding. The lab consists of the following parts: