Zero-Shot End-To-End Spoken Question Answering In Medical Domain

TL;DR

This paper presents a zero-shot end-to-end spoken question answering method for the medical domain, reducing resource use and improving accuracy compared to traditional cascade systems.

Contribution

It introduces a novel zero-shot E2E SQA approach for medical questions, demonstrating significant resource savings and accuracy improvements over traditional methods.

Findings

Up to 14.7 times fewer resources needed

Improved average accuracy by 0.5%

Evaluated on 8 medical tasks with synthetic audio

Abstract

In the rapidly evolving landscape of spoken question-answering (SQA), the integration of large language models (LLMs) has emerged as a transformative development. Conventional approaches often entail the use of separate models for question audio transcription and answer selection, resulting in significant resource utilization and error accumulation. To tackle these challenges, we explore the effectiveness of end-to-end (E2E) methodologies for SQA in the medical domain. Our study introduces a novel zero-shot SQA approach, compared to traditional cascade systems. Through a comprehensive evaluation conducted on a new open benchmark of 8 medical tasks and 48 hours of synthetic audio, we demonstrate that our approach requires up to 14.7 times fewer resources than a combined 1.3B parameters LLM with a 1.55B parameters ASR model while improving average accuracy by 0.5\%. These findings underscore the potential of E2E methodologies for SQA in resource-constrained contexts.