Our motto is ‘We hear everything everywhere and tell everyone who wants to know.’ Something we don’t mention often - but we feel equally proud of - is how we do it: Audio Fingerprinting.
An audio fingerprint is a condensed digital summary of an audio signal, generated by extracting acoustically relevant characteristics of a piece of audio content. Along with matching algorithms, this digital signature permits us to identify different versions of a single recording with the same title.
Fragment of a spectrogram, the image that represents all BMATers saying out loud “Music Innovators”. A spectrogram is the basis for our audio fingerprinting technology.
When a song is ingested into our database, we automatically generate and store its fingerprint which we’ll later use to identify the audio tracks we record across TVs, radios, and venues. Just like with human fingerprints, we compare recorded audio against a global database of acoustic fingerprints and locate its match within seconds.
But as every recording is unique, identifying audio (matching it with its fingerprint and metadata) requires it to be almost identical to the stored and fingerprinted song. However, not strictly identical because good fingerprinting technology must be robust against certain sound degradations and needs to detect when the song isn’t itself anymore.
We believe human perception determines this boundary and we train our technology to develop the same sensitivity. There are several scenarios where music identification presents certain particularities. We optimise our fingerprinting for each use case so that it’s as accurate as possible and at the lowest computational cost. This is why we have an entire fingerprinting family.