Title :
Note Recognition of Polyphonic Music Based on Timbre Model
Author :
Shi, Lixin ; Zhang, Junzxing ; Li, Min
Author_Institution :
Dept. of Electromech. & Inf. Eng., Dalian Nat. Univ., Dalian, China
Abstract :
Note recognition has been studied for many years, and current techniques are still not accurate and robust. Partial overlapping is one of the most difficult problems, all algorithms have trouble in processing the shared partial. In this paper, we analyze the similarity and stability of timbre, and propose a recognition method based on the timbre model. The note can be recognized by calculating the matching rate and the strength, and the partial overlapping problem is solved by employing the proportional subtraction mechanism. The simulation experiments show that the method is accurate and computationally efficient.
Keywords :
acoustic signal processing; music; note matching rate; partial overlapping problem; polyphonic music note recognition; proportional subtraction mechanism; timbre stability model; Cybernetics; Intelligent systems; Man machine systems; Music; Timbre; note recognition; proportional subtraction mechanism; timbre model;
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics, 2009. IHMSC '09. International Conference on
Conference_Location :
Hangzhou, Zhejiang
Print_ISBN :
978-0-7695-3752-8
DOI :
10.1109/IHMSC.2009.52