Electric Guitar Playing Technique Detection in Real-World Recording Based on F0 Sequence Pattern Recognition

For a complete transcription of a guitar performance, the detection of playing techniques such as bend and vibrato is important, because playing techniques suggest how the melody is interpreted through the manipulation of the guitar strings. While existing work mostly focused on playing technique detection for individual single notes, this paper attempts to expand this endeavor to recordings of guitar solo tracks. Specifically, we treat the task as a time sequence pattern recognition problem, and develop a twostage framework for detecting five fundamental playing techniques used by the electric guitar. Given an audio track, the first stage identifies prominent candidates by analyzing the extracted melody contour, and the second stage applies a pre-trained classifier to the candidates for playing technique detection using a set of timbre and pitch features. The effectiveness of the proposed framework is validated on a new dataset comprising of 42 electric guitar solo tracks without accompaniment, each of which covers 10 to 25 notes. The best average F-score achieves 74% in two-fold cross validation. Furthermore, we also evaluate the performance of the proposed framework for bend detection in five studio mixtures, to discuss how it can be applied in transcribing real-world electric guitar solos with accompaniment.