Jazz standards dataset boosts audio beat and chord recognition
JSIR: An Audio-Aligned, Multi-Task Dataset of Jazz Standard Recordings
SoundDigital LibrariesMachine LearningMultimedia
Summary
It can be hard for existing music software to accurately recognize beats, chords, and song sections in jazz music because most datasets focus on pop or rock. The authors created a large new collection of jazz recordings with detailed annotations made by a jazz musician. Using this dataset to train computer models makes them better at tracking beats and chords in jazz music. They also shared their annotations and tools so others can use them too.
What this means in practice
- •For music software developers: Create jazz music apps that more accurately identify beats, chords, and song sections using the new jazz standards dataset.
- •For audio product designers: Enhance music transcription or learning tools to perform better on jazz recordings by integrating models trained with this dataset.
Authors
Sihun Lee, Dasaem Jeong
Abstract
Beat tracking, chord estimation, and structure analysis are staple tasks of music information retrieval. Their datasets are drawn largely from Western popular music, and jazz remains a repertoire on which state-of-the-art systems underperform. We present JSIR, the Jazz Standards dataset for Information Retrieval. Its 267 recordings of 44 jazz standards span 25.6 hours, 3.7 times the audio of JAAH, the closest existing resource. For each recording, we provide annotations for beat and downbeat positions, chords, and sections, all produced by a jazz musician and revised in several passes. In baseline experiments, models trained with JSIR also improve on other jazz datasets: the downbeat F-measure of a state-of-the-art beat tracker rises from 87.7% to 89.2%, and the seventh-chord accuracy of a pop-trained chord estimator on JAAH from 34% to 41%. We publicly release the annotations, the annotation tool used to create them, and a web application that displays them in sync with the audio.