Recently software systems have been proposed to accelerate the progress of singing beginners. The basics of these systems are: the pitch of the sung notes is detected and algorithmic errors removed. Then, an alignment is made with a melodic ground truth, often as a midi representation, using techniques including Dynamic Time Warping and Hidden Markov Models. Although results have been reasonable, significant drawbacks to these alignment schemes include how a “musically acceptable” alignment can be identified, dynamic singer behavior, multiple repeated notes, and dealing with omitted or extra notes. To this end an improved singing analysis system structure is proposed that includes psychoacoustic models and intelligent decision making. Justification is given along with a description of a structured evaluation procedure.
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.
The Engineering Briefs at this Convention were selected on the basis of a submitted synopsis, ensuring that they are of interest to AES members, and are not overly commercial. These briefs have been reproduced from the authors' advance manuscripts, without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for their contents. Paper copies are not available, but any member can freely access these briefs. Members are encouraged to provide comments that enhance their usefulness.