In this paper, a system for automatic transcription of multiple-instrument polyphonic music is proposed, which supports tracking multiple concurrent notes using linear dynamical systems (LDS). The system is based on a spectrogram factorisation model and supports the detection of multiple pitches and instrument contributions. In order to track multiple concurrent pitches, the use of LDS as prior to the multi-pitch model is proposed. LDS parameters are learned using score-informed transcriptions; for inference, online and offline LDS variants are evaluated. The MAPS and Bach10 datasets are used for experiments. Results show that the proposed LDS-based method can successfully track multiple concurrent notes, leading to an improvement of over 3% in terms of F-measure for both datasets over benchmark note tracking approaches.
https://www.aes.org/e-lib/browse.cfm?elib=18760
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.
Learn more about the AES E-Library
Start a discussion about this paper!
