DISQUS

Digital Before Digital: Discussion: Google Must Be Close to Indexing Video Content

  • Charles Eichenbaum · 1 year ago
    There are probably certain elements of human speech that can be keyed in on (cadence, dynamic modulation, individual’s tone) that differ from ambient noise and music. This might help them isolate the spoken parts of the videos – which in turn might allow them to convert the text to speech and index. They could even try to catalog all known / published video media and try to create some Shazam style identifier to further ID the content (is this “Dude Where’s My Car,” or “amateur” video).I bet you’re right.
  • Chris Brogan... · 1 year ago
    You know that GOOG-411 is a big voice-training software, right? Further, you've heard of http://everyzing.com , true? There are LOTS of speech-rec services that can catalog the audio stream of a video. There are pattern-rec and visual-rec softwares already leaking into the mainstream that can track faces, certain keyed objects, etc.

    They're doing it. It's just not ready for beta. : )
  • schneidermike · 1 year ago
    Hah! Sweet validation! I knew it. Thanks for weighing in Chris.