# Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation

## TL;DR

This paper presents an adversarial domain adaptation approach to reduce the impact of speech recognition errors on spoken question answering, improving accuracy by aligning ASR hypotheses with reference transcriptions.

## Contribution

It introduces an adversarial model for domain adaptation that learns domain-invariant features to mitigate ASR errors in spoken QA systems.

## Key findings

- Achieved a 2% improvement in EM score over previous models.
- Demonstrated the effectiveness of adversarial domain adaptation in SQA.
- Improved robustness of spoken QA against ASR errors.

## Abstract

Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work proposes to mitigate the ASR errors by aligning the mismatch between ASR hypotheses and their corresponding reference transcriptions. An adversarial model is applied to this domain adaptation task, which forces the model to learn domain-invariant features the QA model can effectively utilize in order to improve the SQA results. The experiments successfully demonstrate the effectiveness of our proposed model, and the results are better than the previous best model by 2% EM score.