Fig. 1
From: Efficient music identification using ORB descriptors of the spectrogram image
Audio fingerprint system. This figure shows the general audio fingerprinting system done by previous authors. The algorithms generally followed this approach where the raw audio would be captured (by loading the audio signal or by microphone). The audio signal is then processed into a digital format where the audio fingerprints are extracted. The audio fingerprints of songs that were similarly processed and stored in a database are then compared by some algorithm to execute a database lookup. After the resulting audio fingerprint comparison is done, the corresponding song information for the highest match is returned