SD-QA: Spoken Dialectal Question Answering for the Real World
This addresses the gap in real-world QA systems for diverse users, though it is incremental as it builds on existing datasets.
The authors tackled the problem that current QA benchmarks ignore speech recognition errors and user dialects, by creating a multi-dialect spoken QA dataset with over 68k audio prompts in 24 dialects across five languages, and provided baseline results analyzing performance and fairness.
Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces. However, current benchmarks in QA research do not account for the errors that speech recognition models might introduce, nor do they consider the language variations (dialects) of the users. To address this gap, we augment an existing QA dataset to construct a multi-dialect, spoken QA benchmark on five languages (Arabic, Bengali, English, Kiswahili, Korean) with more than 68k audio prompts in 24 dialects from 255 speakers. We provide baseline results showcasing the real-world performance of QA systems and analyze the effect of language variety and other sensitive speaker attributes on downstream performance. Last, we study the fairness of the ASR and QA models with respect to the underlying user populations. The dataset, model outputs, and code for reproducing all our experiments are available: https://github.com/ffaisal93/SD-QA.