Integrate Document Ranking Information into Confidence Measure Calculation for Spoken Term Detection

TL;DR

This paper introduces a novel algorithm that enhances confidence measure calculation in spoken term detection by integrating document relevance information, leading to improved accuracy across multiple languages and robustness with limited resources.

Contribution

The paper presents a new method that combines document ranking with confidence measures, improving STD performance especially in resource-limited language scenarios.

Findings

Consistent improvement over state-of-the-art methods

Effective across Tamil, Vietnamese, and English

Robust even with less accurate speech recognizers

Abstract

This paper proposes an algorithm to improve the calculation of confidence measure for spoken term detection (STD). Given an input query term, the algorithm first calculates a measurement named document ranking weight for each document in the speech database to reflect its relevance with the query term by summing all the confidence measures of the hypothesized term occurrences in this document. The confidence measure of each term occurrence is then re-estimated through linear interpolation with the calculated document ranking weight to improve its reliability by integrating document-level information. Experiments are conducted on three standard STD tasks for Tamil, Vietnamese and English respectively. The experimental results all demonstrate that the proposed algorithm achieves consistent improvements over the state-of-the-art method for confidence measure calculation. Furthermore, this algorithm is still effective even if a high accuracy speech recognizer is not available, which makes it applicable for the languages with limited speech resources.