Decline of the state of infrastructure in North America due to aging over the past decades has spawned burgeoning interest in the detection of internal damage of reinforced concrete (RC) structures via nondestructive testing. This study proposes a new impact-echo analysis method using wavelet transforms. The signals recorded from the microphones are analyzed using percentage of energy information to detect in-situ damages. Further, an artificial neural network (ANN) was used in order to test the feasibility of increasing the automaticity of the impact-echo method and a semi-autonomous sensing setup was used to the same end. The proposed wavelet transform-based approach showed improved accuracy when covering broader areas over conventional methods. The use of an ANN removed the need for a user-defined cutoff value for the classification of intact and damaged locations when a least-squared distance approach was used. It is postulated that this may contribute significantly to testing time reduction.