The Google Blog says.“We’ve built machine learning models that can match your hum, whistle or singing to the right ‘fingerprint’.”“When you hum a melody into Search, our machine learning models transform the audio into a number-based sequence representing the song’s melody, models are trained to identify songs based on a variety of sources, including humans singing, whistling or humming, as well as studio recordings,” the post continues.“The algorithms also take away all the other details, like accompanying instruments and the voice’s timbre and tone.
What we’re left with is the song’s number-based sequence, or the fingerprint.” The feature is currently available on both iOS and Android, with the latter providing the feature in over 20.
Read more on nme.com