Arpi Mardirossian

Here is a great video by OK Go for Skyscrapers that features a sultry montage of dance moves through a series of colorful urban backdrops. The clip was directed and produced by Grammy Award-winning choreographer and director Trish Sie.

Ever since my days in MIR research, I have been fascinated by musical renditions. This fascination emerged because I realized that renditions were great test pieces for my music similarity algorithms. Now that I don’t have a practical need for renditions, I have begun to appreciate them and wonder about their less tangible qualities. I find it so interesting that even though the core song remains the same, the changing of other musical qualities can sometimes completely alter the listening experience and emotions that are evoked by the piece. To demonstrate, I have compiled 10 renditions of the song ‘Bang Bang’. This song was first recorded by Cher in 1966 even though the more well known version is by Nancy Sinatra who covered it in the same year. My favorite version is by Le Bang Bang. Get the playlist on Grooveshark

A new playlist for a new year. Cheers! Get the playlist on Grooveshark

I’ve been playing around with different ways to explore/share music lately. I’m really liking the Grooveshark option. Check out my first playlist!

The British Journal of Photography has published the Tagasauris story on its site. Check it out here!

I am very proud to announce the launch of Tagasauris. We have been working hard to develop innovative solutions for unlocking the value of multimedia collections by improving find-ability through quick, cost-effective and accurate descriptive labels. Tagasauris is a media tagging tool that’s powered by the crowd. We provide superior quality tags at lightening speed for a fraction of the cost of more traditional methods. We also connect these tags to well defined concepts and metadata with unique URLs. This means that everybody uses the same names for tags from the world’s largest collection of knowledge.

I am proud to announce the launch of the Freddie Katz site (designed and developed in collaboration with Tocarte). Freddie Katz is a NYC based producer/sound engineer/axe slinger!

On 06.24.2010 and 06.25.2010 we shot video footage for the music visualization application at the Zemeckis Center. We got some excellent footage (I will post some samples soon) and had fun working with all the wonderful dancers.

Music visualization can be successfully used to dramatically enhance the music listening experience by providing a visual pairing that presents aesthetically pleasing imagery, reinforces emotions and moods evoked by the music, and reveals information about the features and structure of the music. The most basic and instinctive visualization of music is dance. Dance is defined as: “moving rhythmically to music, using prescribed or improvised steps and gestures”. I am currently developing my vision of a dance based music visualization for Classical KUSC.

This visualization application will dynamically synchronize stylized dances (dancer silhouettes on a variety of backgrounds) to music to create the effect that a dancer is dancing to the user’s music selection. We have recorded video footage against a green screen of professional dancers in a variety of dance styles including hip hop, break dancing, classical Indian, Brazilian, salsa, African and bollywood. For each dancer, we have recorded a set of dance sequences of varying lengths. These sequences will be chained together in different combinations to create a variety of dances. These dances can potentially be paired with any piece of music. A dance will be synchronized to a piece of music by compressing and contracting portions of the video to align the underlying beats of the dance to that of the music.

I have the pleasure to be working with some brilliant and dedicated USC collaborators:
Michael Annetta (grad student – MFA in Interactive Media)
Ravi Nitin Balajee (grad student – MS in Electrical Engineering)
Elaine Chew (faculty member – Industrial and Systems Engineering)
Andreas Kratky (faculty member – School of Cinematic Arts)
James Taylor (grad student – MFA in Interactive Media)

I have been working with Tocarte on the development of a high performance annotation solution that makes images more discoverable and connected. The system also helps optimize both productivity and accuracy of crowd-sourced workers. It goes beyond simple free-text tags and associates strong IDs to unique, well-defined concepts and metadata.