Language Modeling for Multi-Domain Speech-Driven Text Retrieval

TL;DR

This paper presents a method for improving speech-driven text retrieval across multiple domains by customizing language models based on the target collection, leading to better recognition and retrieval accuracy.

Contribution

The study introduces a domain-specific language modeling approach tailored for speech-driven retrieval systems, enhancing performance over generic models.

Findings

Improved speech recognition accuracy in multi-domain retrieval tasks.

Enhanced retrieval precision using collection-specific language models.

Effective integration of speech recognition and retrieval processes.

Abstract

We report experimental results associated with speech-driven text retrieval, which facilitates retrieving information in multiple domains with spoken queries. Since users speak contents related to a target collection, we produce 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.