This study describes a system which detects clicks in sound (audible degradations). The system is based on a computational model of the peripheral ear. In order to train and verify the system, a listening test was conducted using 89 short samples of analog (vinyl) records. The samples contained singing voice, music (rock’n’roll), or both. We randomly chose 30 samples from the set and used it to train the system; then we tested the system using the 59 remaining samples. The system performance expressed as a percentage of correct detections (78.1%) and false alarms (3.9%) is promising.

Download