The process of vocal extraction from musical tracks using panning information was implemented and presented in the paper. An enhancement to refine the extraction process and its impact on the performance measures were analyzed. Based on the performance measures it was observed that the introduced enhancement contributed to a significant improvement in the extraction process evident in the increased Signal to Interference Ration (SIR) rating. A Karaoke system design which works for commercial stereophonic audio tracks, is proposed which can serve as a musical learning aid for amateurs.
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.