Mood & Music

Thanks Paul, for another mention on Duke Listens!. It appears that mood is gaining momentum as an alternative form of music classification and music recommendation.

Thesis!!!

My Master's thesis at the MIT Media Laboratory is now complete! Here is the abstract:

Mood classification of music is an emerging domain of music information retrieval. In the approach presented here features extracted from an audio file are used in combination with the affective value of song lyrics to map a song onto a psychologically based emotion space. The motivation behind this system is the lack of intuitive and contextually aware playlist generation tools available to music listeners. The need for such tools is made obvious by the fact that digital music libraries are constantly expanding, thus making it increasingly difficult to recall a particular song in the library or to create a playlist for a specific event. By combining audio content information with context-aware data, such as song lyrics, this system allows the listener to automatically generate a playlist to suit their current activity or mood.

Please visit my thesis page for more information. I will hopefully be posting the entire document and some cool apps in the near future.

Thesis Proposal

Title: A Mood-Based Music Classification and Exploration System

Abstract:
Mood classification is very subjective. There have been many psychological studies performed throughout the past century relating to music and emotion, and as a result there exist many different representations of human emotion. This thesis proposes to utilize the best possible psychological model of emotion by incorporating the findings of these studies into an innovative front-end for a digital music library where music can be queried, browsed, and explored by mood, rather than artist, album, or genre. With the use of state-of-the-art audio and textual analysis tools this work proposes to automatically and accurately classify music by mood.

+++++++++++++++++++++++++++++++++++++++

Let me know what you think of the idea!

Officially Blogged

I have now officially had my first blog appearance, thanks to Paul Lamere of Duke Listens!. Feels good!

He makes note of my Lyricator software, which derives the affective value of lyrics.

Enjoy!

MIT Media Lab

Welcome to my blog.

I am now at the MIT Media Lab in Cambridge, MA, USA.

Click here for the latest.

If you're looking for my research on cubase, mtc, midi clock and synchronization, you can now find it here: musictech2.blogspot.com.

Owen.