Slashdot Mirror

← Back to Stories (view on slashdot.org)

An AI System For Editing Music in Videos (mit.edu)

Posted by msmash on from the how-about-that dept.

Amateur and professional musicians alike may spend hours poring over YouTube clips to figure out exactly how to play certain parts of their favorite songs. But what if there were a way to play a video and isolate the only instrument you wanted to hear? MIT News: That's the outcome of a new AI project out of MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL): a deep-learning system that can look at a video of a musical performance, and isolate the sounds of specific instruments and make them louder or softer. The system, which is "self-supervised," doesn't require any human annotations on what the instruments are or what they sound like. Trained on over 60 hours of videos, the "PixelPlayer" system can view a never-before-seen musical performance, identify specific instruments at pixel level, and extract the sounds that are associated with those instruments. For example, it can take a video of a tuba and a trumpet playing the "Super Mario Brothers" theme song, and separate out the soundwaves associated with each instrument. The researchers say that the ability to change the volume of individual instruments means that in the future, systems like this could potentially help engineers improve the audio quality of old concert footage. You could even imagine producers taking specific instrument parts and previewing what they would sound like with other instruments (i.e. an electric guitar swapped in for an acoustic one).

9 of 31 comments (clear)

  1. It's 'poring', not 'pouring' by imidan · · Score: 4, Informative

    Amateur and professional musicians alike may spend hours pouring over YouTube clips

    Really? What substance do they pour over the clips? And to what end? Do they pour a liquid, like coffee? Or a fluid-like solid, like sand?

    I'm sorry. Pouring vs poring is one that really bugs me, for some reason.

    1. Re:It's 'poring', not 'pouring' by drinkypoo · · Score: 2

      What's especially pathetic is that Trump is being mocked world-wide for making the same error in a tweet recently, and slipshod.org here just copied his embarrassing mistake, bigly. Sad!

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  2. This is so powerful ... by CaptainDork · · Score: 2

    ... it can isolate first chair clarinet farting.

    --
    It little behooves the best of us to comment on the rest of us.
  3. There is nothing more important... by Arzaboa · · Score: 2

    ...than being able to re-edit video game sound tracks.

    --
    "A trumpet says what?" - H. Stern

  4. Whoa! by 110010001000 · · Score: 2

    It can do image recognition frequency filtering and change the volume too? AI is amazing. I am so glad I live in 2018! One of these days these AI experts are gonna make AI do something really useful, and then watch out! The sky is the limit!

  5. Identifying a sound at "pixel level" by ayesnymous · · Score: 3, Insightful

    What does that mean?

  6. Re:Challenge by q_e_t · · Score: 2

    Can I remove all the sound from modern pop 'music'?

  7. Mmmmh by nospam007 · · Score: 2

    I'm sure they can be fooled by playback, when the musicians only fake the playing.

  8. Re: 60 hours? by Hognoxious · · Score: 2

    Do you write your posts in Mandarin using a brick, then OCR them and translate them manually into Welsh then dictate them to someone from New Guinea who types them in for you?

    --
    Confucius say, "Find worm in apple - bad. Find half a worm - worse."