Paper: Anchored Speech Recognition for Question Answering

ACL ID N09-2067
Title Anchored Speech Recognition for Question Answering
Venue Human Language Technologies
Session Short Paper
Year 2009

In this paper, we propose a novel question answering system that searches for responses from spoken documents such as broadcast news stories and conversations. We propose a novel two-step approach, which we refer to as anchored speech recognition, to improve the speech recognition of the sentence that sup- ports the answer. In the first step, the sen- tence that is highly likely to contain the an- swer is retrieved among the spoken data that has been transcribed using a generic automatic speech recognition (ASR) system. This candi- date sentence is then re-recognized in the sec- ond step by constraining the ASR search space using the lexical information in the question. Our analysis showed that ASR errors caused a 35% degradation in the performance of the question answering system. Experim...