Singing Voice Separation Combining Panning Information and Pitch Tracking
Source Separation techniques applied to music mixtures are able to extract relevant nformation that can be very useful for many applications, such as music remixing and reprocessing, lyrics recognition or music information retrieval. Among all the sources present in modern music themes, singing voice has an especial interest because it is the only one that combines music, lyrics and expression. In this paper, we propose a system designed for extracting singing voice from stereo recordings in different steps. This system combines panning information and pitch tracking, allowing to refine the time-frequency mask applied for extracting a vocal segment, and thus, improving the separation. An application example is discussed.
Click to purchase paper 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 $20 for non-members, $5 for AES members and is free for E-Library subscribers.