This paper introduces speech-based visual question answering (VQA), the task of generating an answer given an image and a spoken question. Two methods are studied: an end-to-end, deep neural network that directly uses audio waveforms as input versus a pipelined approach that performs ASR (Automatic Speech Recognition) on the question, followed by text-based visual question answering. Furthermore, we investigate the robustness of both methods by injecting various levels of noise into the spoken question and find both methods to be tolerate noise at similar levels.
@article{arxiv.1705.00464,
title = {Speech-Based Visual Question Answering},
author = {Ted Zhang and Dengxin Dai and Tinne Tuytelaars and Marie-Francine Moens and Luc Van Gool},
journal= {arXiv preprint arXiv:1705.00464},
year = {2017}
}