A Normalized-Cut Alignment Model for Mapping Hierarchical Semantic Structures onto Spoken Documents

摘要

We propose a normalized-cut model for the problem of aligning a known hierarchical browsing structure, e.g., electronic slides of lecture recordings, with the sequential transcripts of the corresponding spoken documents, with the aim to help index and access the latter. This model optimizes a normalized-cut graph-partitioning criterion and considers local tree constraints at the same time. The experimental results show the advantage of this model over Viterbi-like, sequential alignment, under typical speech recognition errors.