<body><iframe src="http://www.blogger.com/navbar.g?targetBlogID=10427331&amp;blogName=playtherecords&amp;publishMode=PUBLISH_MODE_SFTP&amp;navbarType=BLUE&amp;layoutType=CLASSIC&amp;homepageUrl=http%3A%2F%2Fplaytherecords.com%2F&amp;searchRoot=http%3A%2F%2Fblogsearch.google.com%2F" marginwidth="0" marginheight="0" scrolling="no" frameborder="0" height="30px" width="100%" id="navbar-iframe"></iframe> <div id="space-for-ie"></div>

Friday, October 07, 2005

More on Music Analysis

Following up on Chris V's post about automated song analysis, there is a story on Slashdot called Dissecting Songs Down to Their 'Musical Genome'.
The company Pandora Media takes a different tack for its online music-recommendation service. When you tell Pandora a song you like or have bought, it doesn't mine its sales database for records of other purchases by those who have bought the song. Instead, it looks for songs with a similar musical profile, based on a database of 300,000 songs rated on up to 400 characteristicslike rhythmic syncopation, vamping and vocal harmonies
Also relevant is Last.fm which uses a plugin (audioscrobbler) in your media player to record what you listen too and make recommendations about other songs/artists you might like... They even have a netradio webcast that is personalized to you.

I've created a Playtherecords Last.fm Group. If 15 of you join it we get our own custom charts and radio station based on what we listen too. Woot.

0 Comments:

Post a Comment

Links to this post:

Create a Link

<< Home