An initial attempt to improve spoken term detection by learning optimal weights for different indexing features

Abstract

Because different indexing features actually have different discriminative capabilities for spoken term detection and different levels of reliability in recognition, it is reasonable to weight the indexing features in the transcribed lattices differently during spoken term detection. In this paper, we present an initial attempt of using two weighting schemes, one context independent (fixed weight for each feature) and one context dependent(different weights for the same feature in different context). These weights can be learned by optimizing a desired spoken term detection performance measure over a training document set and a training query set. Encouraging initial results based on unigrams of Chinese characters and syllables for the corpus of Mandarin broadcast news were obtained from the preliminary experiments.