Hierarchical Representation Based on Bayesian Nonparametric Tree-Structured Mixture Model for Playing Technique Classification

Chen, Sih-Huei; Wu, Shao-Hui; Lee, Yuan-Shan; Lo, Rocky; Wang, Jia-Ching

doi:10.1145/3126686.3126757

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Su et al (2014) recorded 11,928 single electric guitar notes and investigated features extracted from the cepstrum and phase derivatives to classify 7 playing techniques using an SVM. Follow-up research has managed to improve the accuracy of playing technique recognition for the same dataset using Gaussian hierarchical latent Dirichlet allocation (Chen et al, 2017) and a variational auto-encoder with a Gaussian process (Chen et al, 2018). It is, however, not clear how these methods can detect playing techniques in a real-world guitar solo track, due to the lack of a playing technique localization module.…”

Section: Playing Technique Detectionmentioning

confidence: 99%

TENT: Technique-Embedded Note Tracking for Real-World Guitar Solo Recordings

Chen

et al. 2019

Transactions of the International Society for Music Information Retrieval

View full text Add to dashboard Cite

The employment of playing techniques such as string bend and vibrato in electric guitar performance makes it difficult to transcribe the note events using general note tracking methods. These methods analyze the contour of fundamental frequency computed from a given audio signal, but they do not consider the variation in the contour caused by the playing techniques. To address this issue, we present a model called technique-embedded note tracking (TENT) that uses the result of playing technique detection to inform note event estimation. We evaluate the proposed model on a dataset of 42 unaccompanied lead guitar phrases. Our experiments showed that TENT can nicely recognize complicated skills in monophonic guitar solos and improve the F-score of note event estimation by 14.7% compared to an existing method. For reproducibility, we share the Python source code of our implementation of TENT at the following GitHub repo: https://github.com/srviest/SoloLa.

show abstract

Section: Playing Technique Detectionmentioning

confidence: 99%