audiocaps.github.io/supp

Preview meta tags from the audiocaps.github.io website.

Linked Hostnames

1

Search Engine Appearance

Google

https://audiocaps.github.io/supp

AudioCaps Supplementary

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.



Bing

AudioCaps Supplementary

https://audiocaps.github.io/supp

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.



DuckDuckGo

https://audiocaps.github.io/supp

AudioCaps Supplementary

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.

  • General Meta Tags

    8
    • title
      AudioCaps Supplementary | AudioCaps: Generating Captions for Audios in the Wild
    • charset
      utf-8
    • x-ua-compatible
      ie=edge
    • viewport
      width=device-width, initial-scale=1, shrink-to-fit=no
    • generator
      Gatsby 2.4.5

  • Open Graph Meta Tags

    3
    • og:title
      AudioCaps Supplementary
    • og:description
      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.
    • og:type
      website

  • Twitter Meta Tags

    4
    • twitter:card
      summary
    • twitter:creator
      Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim NAACL-HLT 2019
    • twitter:title
      AudioCaps Supplementary
    • twitter:description
      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.

  • Link Tags

    17
    • apple-touch-icon
      /icons/icon-48x48.png?v=null
    • apple-touch-icon
      /icons/icon-72x72.png?v=null
    • apple-touch-icon
      /icons/icon-96x96.png?v=null
    • apple-touch-icon
      /icons/icon-144x144.png?v=null
    • apple-touch-icon
      /icons/icon-192x192.png?v=null

Links

1