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.
(See document for exact affiliation information.)
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 Join the AES. If you need to check your member status, login to the Member Portal.
