Rapid learning of subjective preference in equalization

We describe and test an algorithm to rapidly learn a listener's desired equalization curve. First, a sound is modified by a series of equalization curves. After each modification, the listener indicates how well the current sound exemplifies a target sound descriptor (e.g., "warm"). After rating, a weighting function is computed where the weight of each channel (frequency band) is proportional to the slope of the regression line between listener responses and within-channel gain. Listeners report that sounds generated using this function capture their intended meaning of the descriptor. Machine ratings generated by computing the similarity of a given curve to the weighting function are highly correlated to listener responses, and asymptotic performance is reached after only ∼25 listener ratings.