Slashdot Mirror

← Back to Stories (view on slashdot.org)

Dictionaraoke - Fair-Use meets Karaoke

Posted by ryuzaki0 on from the amuse-yourself-to-death dept.

stu42j writes "NPR's On the Media today interview's David Dixon from Dictionaraoke.com where 'A group of fair-use artists have created songs using the spoken pronunciation guides of words in online dictionaries. The result is an entertaining blend of computerized music and monotone singing.'"

2 of 104 comments (clear)

  1. Aside from sounding ghastly, it's a political goal by 2Flower · · Score: 4, Insightful

    I'm surprised nobody's really picked up on this -- the radio interviewer even disregarded it ("Putting aside the politics, insert smarky comment here").

    It does call into question the nature of copyright, once you break something down to its core elements. The reason why MIDI was used? Because it's a mathematical representation of a string of notes, rather than a copy of an actual copyrighted performance of those notes. The reason why dictionary samples were used instead of a better synthesizer? Well, think about this: are the sampled words copyrighted? The dictionary sites they were lifted from could claim copyright, but do they really own the rights to a sound bite of a proununciation of an english word? What if I recorded myself saying it? What if you take their recordings and make sentences, who owns the rights then, the composer/assembler or the dictionary or what?

    I LOVE how jumbled the legal issues get surrounding this. Of course, I'm sure the RIAA will get them shut down ASAP to prove they own the right to every aspect of our culture, including our own commentary upon that culture.

  2. Death of the music industry by Animats · · Score: 3, Insightful
    This is an important idea that doesn't work very well yet. When it does, it will kill the music industry.

    First, computer-generated singing from MIDI files can be done better. Listen to Festival Singer, from the Oregon Graduate University of Science and Technology, which is in turn based on a speech system from the University of Edinburgh. It's still not that great, but progress is being made. They're approaching the garage-band level.

    More components are needed to make computer-generated music more human-like. Some of that work has been done. The Media Lab system for Expressive Performance Extraction takes in a MIDI file and an audio recording of piano music, and builds a model of the performer's expression. This model can then be used with other MIDI files to mimic the specific pianist.

    The next big step is to do that for singers.

    The goal is to have a system where you put in a MIDI file, lyrics, performer and singer models, and push start. Out comes a performance that sounds like a good backup band.

    Because the music industry likes to have the option to replace performers, copyright law doesn't prevent doing this on popular music. You only have to pay a modest statutory royalty to the original songwriter.

    Once this works, it could make a real dent in the music industry. Performers could go the way of orators. People would still go to live performances, but we could dispense with much of the recorded music industry.