SISO and SIMO Accompaniment Cancellation for Live Solo Recordings Based on Short-Time ERB-Band Wiener Filtering and Spectral Subtraction
This addresses a specific problem in collaborative music learning for apprentices seeking self-assessment or machine-aided analysis, but it is incremental as it builds on classical filtering methods.
The paper tackled the problem of suppressing accompaniment in live solo recordings for music learning by comparing adaptive and Wiener filtering approaches, finding that Wiener filtering in the short-time Fourier transform domain is more effective and computationally cheap when using auditory filter bands.
Research in collaborative music learning is subject to unresolved problems demanding new technological solutions. One such problem poses the suppression of the accompaniment in a live recording of a performance during practice, which can be for the purposes of self-assessment or further machine-aided analysis. Being able to separate a solo from the accompaniment allows to create learning agents that may act as personal tutors and help the apprentice improve his or her technique. First, we start from the classical adaptive noise cancelling approach, and adjust it to the problem at hand. In a second step, we compare some adaptive and Wiener filtering approaches and assess their performances on the task. Our findings underpin that adaptive filtering is inapt of dealing with music signals and that Wiener filtering in the short-time Fourier transform domain is a much more effective approach. In addition, it is very cheap if carried out in the frequency bands of auditory filters. A double-output extension based on maximal-ratio combining is also proposed.