The modulation spectrum is a promising method to incorporate dynamic information in pattern classification. It contains important cues about the nonstationary content of a signal and yields complementary improvements when it is combined with conventional features derived from short-term analysis. Many prior modulation spectrum approaches are based on uniform modulation frequency decomposition. The drawbacks of these approaches are high dimensionality and a lack of a connection to human perception of modulation. This paper presents multi-scale modulation frequency decomposition and shows an improvement over standard modulation spectrum in a digital communication signal classification task. Features derived from this representation provide lower classification error rates than those from a constant-bandwidth modulation spectrum whether used alone or in combination with short-term features.