Quantization is a central issue in automatic music transcription programs which convert a musical performance into music notation. Commercially available packages are still quite unsuccessful in this respect. A report on the development of a robust quantizer is given which makes use of recursive vector quantization based on data from perceptual experiments and a statistical characterization of scores and performances.
https://www.aes.org/e-lib/browse.cfm?elib=8275
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!