Classifier-based system combination for spoken term detection

摘要

Systems and methods for processing a query include determining a plurality of sets of match candidates for a query using a processor, each of the plurality of sets of match candidates being independently determined from a plurality of diverse word lattice generation components of different type. The plurality of sets of match candidates is merged by generating a first score for each match candidate to provide a merged set of match candidates. A second score is computed for each match candidate of the merged set based upon features of that match candidate. The first score and the second score are combined to provide a final set of match candidates as matches to the query.

主权项

1. A method for processing a query, comprising:
determining a plurality of different sets of match candidates for a query from an audio collection using a processor, each of the plurality of different sets of match candidates being independently determined from a plurality of different word lattice generation components, each of the plurality of different word lattice generation components providing a different word lattice as a representation of multiple word hypotheses in a directed acyclic graph; generating a first score for each match candidate; merging the plurality of different sets of match candidates into a merged set of all match candidates, where overlapping match candidates from different sets are merged into a single match candidate in the merged set; computing a second score for each match candidate of the merged set based upon features of that match candidate; and combining the first score and the second score to identify a final set of match candidates with a combined score above a threshold as matches to the query.