Google’s Hum To Search Feature Is Here To Make Searching For Songs Easier

When Shazam was released for the first time, the entire smartphone community breathed a sigh of relief because the app let users search for songs by making the app listen to what is being played in your surroundings.  Since then finding new songs and genres has become easier as searching for songs at your favourite clubs or at a friend’s party is now at one’s fingertips.  But, what if you only know a piece of music or a tune which is stuck in your head and no way to identify the song.

Google is making it possible to try to find a song with its new feature called ‘hum to search.’  The feature can listen to humming, whistling or singing to identify songs.  ‘Hum to search’ is triggered when you ask Google “what is this song?” and then proceed to perform bits of the tune to the best of your ability.  Google will then present a list of songs according to a percentage match score which comes closest to your performance.

ALSO READ: Google Relents By Deferring 30% Play Store App Fee For Developers 

Google’s machine learning algorithm converts the audio input into a numbers based sequence which it then matches with other song melodies and tries to find the closest matching tune.  The model was trained with several sources with actual people singing, humming and whistling in addition to real studio recordings.  Google’s algorithms can also strip away musical instruments, as well as the timbre and tone of the singer’s voice in order so it only relies on the actual numeric sequence in the song matching process.

The ‘hum to search’ option is live and currently supports more than twenty languages.  While the feature might seem minor in terms of utility it makes up for improving the quality of life on a major level.  Google has once again proved to the world as to why it is the best company out there with their ‘hum to search’ feature.