The purpose of this research is to propose a low cost general model-based method such that musical sounds can be closely synthesized by analyzing the recorded signal generated by target acoustic instruments. A recurrent neural network based technique is used to search the suitable synthesis parameters so that synthetic results can sound very close to the target instruments.
(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.
