Speech-Driven Text Retrieval: Using Target IR Collections for Statistical Language Model Adaptation in Speech Recognition

TL;DR

This paper presents a method to improve speech-driven text retrieval by adapting speech recognition language models to target collections, enhancing both recognition and retrieval accuracy in practical applications.

Contribution

It introduces a novel approach to adapt statistical language models for speech recognition based on target collections, specifically for speech-driven text retrieval.

Findings

Adaptation improves recognition accuracy

Enhanced retrieval performance observed

Effective with existing test collections

Abstract

Speech recognition has of late become a practical technology for real world applications. Aiming at speech-driven text retrieval, which facilitates retrieving information with spoken queries, we propose a method to integrate speech recognition and retrieval methods. Since users speak contents related to a target collection, we adapt statistical language models used for speech recognition based on the target collection, so as to improve both the recognition and retrieval accuracy. Experiments using existing test collections combined with dictated queries showed the effectiveness of our method.