AudioCaps: Generating Captions for Audios in the Wild

We explore the problem of audio captioning: generating natural language description for any kind of audio in the wild.We contribute a large-scale dataset of about 46K audio clips to human-written text pairs collected via crowdsourcing on the AudioSet dataset.We show that our collected captions are indeed faithful for audio inputs and discover what forms of audio representation and captioning models are effective for the audio captioning.