SYSTEM AND METHOD OF LATTICE-BASED SEARCH FOR SPOKEN UTTERANCE RETRIEVAL

摘要

A system and method are disclosed for retrieving audio segments from a spok en document. The spoken document preferably is one having moderate word error rates such as telephone calls or teleconferences. The method comprises converting speech associated with a spoken document into a lattice representation and indexing the lattice representation of speech. These steps are performed typically off line. Upon receiving a query from a user, the method further comprises searching the indexed lattic e representation of speech and returning retrieved audio segments from the spoken document that match the user query.