Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering. (arXiv:2204.09634v2 [cs.SD] UPDATED)

Web: http://arxiv.org/abs/2204.09634

Audio question answering (AQA) is a multimodal translation task where a
system analyzes an audio signal and a natural language question, to generate a
desirable natural language answer. In this paper, we introduce Clotho-AQA, a
dataset for Audio question answering consisting of 1991 audio files each
between 15 to 30 seconds in duration selected from the Clotho dataset. For each
audio file, we collect six different questions and corresponding answers by
crowdsourcing using Amazon Mechanical Turk. The questions and answers …

arxiv audio dataset question answering