Skip to content

Algorithms for lead guitar transcription considering expression style

Notifications You must be signed in to change notification settings

yunjiewang/SoloLa

 
 

Repository files navigation

image

================================================================================

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

image

Requirements

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

Author

Yuan-Ping Chen, Ting-Wei Su

References

About

Algorithms for lead guitar transcription considering expression style

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.3%
  • Shell 0.7%