Papers › Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by...

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

16 Apr 2019arXiv:1904.07904archive 2025-07-28

Chia-Hsuan Lee, Yun-Nung Chen, Hung-Yi Lee

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.

PaperPDFCode

Code

chia-hsuan-lee/spoken-squad mentioned on GitHubNOASSERTION report
chiahsuan156/Spoken-SQuAD mentioned on GitHubNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationQuestion AnsweringSpeech RecognitionSpoken Language Understandingspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Spoken Language Understanding Spoken-SQuAD QANet + GAN F1 score 63.11 #3 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections