GuitarFace

By Roshan Vid and Gina Collecchia

Goals

To identify virtuosity in rock guitar solos by analyzing MIDI data with supervised learning (SVM).

Motivation

Rock music is one of the largest genres of music, but there are individual artists who stand out as titans in the genre. Led Zeppelin, The Doors, and Jimi Hendrix are just a few examples of bands that truly convey masterfulness in the genre. The guitar is frequently given the spotlight of a rock band. Rock and roll has some core instruments: the electric guitar, bass, drums, and voice. We could compare it to other genres on a basis of instrumentation, and find some differentiation. For example, jazz would have a noisier distribution of instruments: perhaps a peak over drums and the trumpet, but would we see the same over the piano and guitar?

Similarly, there are other features besides instrumentation that are core to rock, and furthermore rock guitar soloing:

• scale / key / intonation
• timing
• dynamic range (loudness)
• pitch range
• repetitiveness
• non-pitched decorations
• vibrato, bend
• stage presence (physical movements, facial expression)
• use of pedals / FX
• music theory of the context, expectation (build-up and violation)
• creativity

All of these features, when performed well or they fall flat, can completely make or break a song. Naturally, we are interested in the measure of quality: what makes a good guitar solo? By "good", we mean retains our interest, impresses, and even inspires.

Since making statements about style are generally difficult, we wondered if just a few or even one of these vectors could provide enough information to differentiate between good and bad guitar soloing. A particularly convincing one is the pitch content (melody) of the solo, knowing what we do about major and minor keys and other scales. Violating the musical scale is one of the clearest violations of our expectations.

Ultimately, we hope to implement our model in the form of a game. It makes sense that actually playing the game should inform us further, since our players will be providing quality data.

, we hoped to generalize these vectors to all improvisation and make some game that rewarded good solos