Gammatone filterbank based energy masking algorithm for active hearing protection system

The difficulty of active hearing protection system is to mask the dangerous noise energy and retain the useful signal at the same time. Binary mask, which was an effective method to be used in speech segregation, was proposed to micro active hearing protection system. A new gammatone filterbank approximation with less resource requirement was proposed to decompose the mixture signal into auditory segments for wearable system. The cue of energy was extracted in segments. Then energy based masking algorithm was used to remove the big noise energy segments. We found that both noise masking and signal reconstruction are effective.