Francesco Foscarin, Jan Schlüter, Gerhard Widmer,
"Beat this! Accurate beat tracking without DBN postprocessing"
: nternational Society for Music Information Retrieval Conference (ISMIR), 2024
Original Titel:
Beat this! Accurate beat tracking without DBN postprocessing
Sprache des Titels:
Englisch
Original Buchtitel:
nternational Society for Music Information Retrieval Conference (ISMIR)
Original Kurzfassung:
We propose a system for tracking beats and downbeats with two objectives: generality across a diverse music range, and high accuracy. We achieve generality by training on multiple datasets -- including solo instrument recordings, pieces with time signature changes, and classical music with high tempo variations -- and by removing the commonly used Dynamic Bayesian Network (DBN) postprocessing, which introduces constraints on the meter and tempo. For high accuracy, among other improvements, we develop a loss function tolerant to small time shifts of annotations, and an architecture alternating convolutions with transformers either over frequency or time. Our system surpasses the current state of the art in F1 score despite using no DBN. However, it can still fail, especially for difficult and underrepresented genres, and performs worse on continuity metrics, so we publish our model, code, and preprocessed datasets, and invite others to beat this.
Forschungs-