Modern digital hearing aid technology that is heavily optimized for speech intelligibility often makes music unlistenable, so that hearing aid wearers often prefer to remove their hearing aids when listening to music. The effects of hearing aid processing on musical signals and on the perception of music have received very little attention. There is no standard test of music perception, and to make the problem more difficult, different musical styles thrive in strikingly different acoustical environments. There have been some studies on the effect of reduced bandwidth on the perceived quality of music, but no systematic evaluation of the effects of dynamic range compression, the most ubiquitous form of gain compensation in digital hearing aids. In this report we present a novel approach to hearing aid fitting applied to both individual differences in hearing impairment and differences among musical styles. The method uses a subjective space approach to reduce the dimensionality of the fitting problem and a non-linear regression technology to interpolate among hearing aid parameter settings. This listener-driven method provides not only a technique for optimal aid fitting, but also information on individual differences and the effects of gain compensation on different musical styles.