SoloLa! is an automatic system for transforming lead guitar audio signal in music recording into sheet music, which features automatic guitar expression style recognition.

The system comprises of the following processing bloakcs:

1. Source Separation - isolate the audio signal of guitar solo from mixture
2. Melody Extraction - estimate the fundamental frequency corresponding to the pitch of the lead guitar to generate a series of consecutive pitch values which are continuous in both time and frequency, a.k.a. melody contour
3. Note Tracking - track the estimated melody contour to recognize discrete musical note events
4. Expression Style Recognition - the detection of applied lead guitar playing techniques such as string bend, slide and vibrato
5. Fingering Arrangement - maps the sequence of notes to a set of guitar fretboard positions

• Melody contour plot reproduced from J. Salamon, E. Gómez, D. P. W. Ellis and G. Richard, "Melody Extraction from Polyphonic Music Signals: Approaches, Applications and Challenges", IEEE Signal Processing Magazine, 31(2):118-134, Mar. 2014 with permission from the authors.

• numpy
• scipy
• ESSENTIA
• librosa
• theano
• Lasagne
• scikit-learn

- mir_eval .. - cython .. - nose .. - networkx .. - madmom

Yuan-Ping Chen, Ting-Wei Su