A framework for using continuous wavelet transforms to isolate and extract blade–vortex interaction noise from helicopter acoustic signals is described. The extraction method allows for the investigation of blade–vortex interactions independent of other sound sources. Experimentally acquired acoustic data from full-scale helicopter flyover tests are first transformed into time-frequency space through the wavelet transformation, with blade–vortex interactions identified and filtered by their high-amplitude, high-frequency impulsive content. The filtered wavelet coefficients are then used to create a pressure signal solely related to blade–vortex interactions. Analysis of a synthetic data set is conducted and shows that blade–vortex interactions can be accurately extracted so long as the blade–vortex interaction wavelet energy is comparable to the wavelet energy in the main rotor harmonic.