Gearbox condition monitoring (CM) plays a significant role in ensuring the operational reliability and efficiency of a wide range of critical industrial systems such as wind turbines and helicopters. Accurate and timely diagnosis of gear faults will improve the maintenance of gearboxes operating under sub-optimal conditions, avoid excessive energy consumption and prevent avoidable damages to systems. This study focuses on developing CM for a multi-stage helical gearbox using airborne sound. Based on signal phase alignments, Modulation Signal Bispectrum (MSB) analysis allows random noise and interrupting events in sound signals to be suppressed greatly and obtains nonlinear modulation features in association with gear dynamics. MSB coherence is evaluated for selecting the reliable bi-spectral peaks for indication of gear deterioration. A run-to-failure test of two industrial gearboxes was tested under various loading conditions. Two omnidirectional microphones were fixed near the gearboxes to sense acoustic information during operation. It has been shown that compared against vibration based CM, acoustics can perceive the responses of vibration in a larger areas and contains more comprehensive and stable information related to gear dynamics variation due to wear. Also, the MSB magnitude peaks at the first three harmonic components of gear mesh and rotation components are demonstrated to be sufficient in characterizing the gradual deterioration of gear transmission. Consequently, the combining of MSB peaks with baseline normalization yields more accurate monitoring trends and diagnostics, allowing the gradual deterioration process and gear wear location to be represented more consistently.