It happens to the best of us, literally on a daily basis; You hear a song, whether in passing or on repeat on a public sound system, you absolutely love it, but you are completely clueless as to who is behind the bop.
Aside from checking your favorite radio station's playlist (and you're already too late to Shazam it), what options do you have? Enter Google's "Hum To Search."
Announced October 16 at Google's Search On event, users can now search for a song just by singing, humming or whistling the part of the tune stuck in your head. You can access the feature by opening the ‘Google Search’ app or using the Google Search Widget and clicking on the microphone icon. You can then ask “what’s this song?” or click the ‘Search a song’ button.
The Google Blog explains the functionality of the new search feature as being similar to fingerprint technology. "We've built machine learning models that can match your hum, whistle or singing to the right ‘fingerprint’," they say.
"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," Google clarifies.
"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."
Looking outside the box a little here, but this feature could also prove to be a valuable resource for songwriters and musicians who have sneaky suspicions that the song they just wrote might sound a little too similar to one they've heard before -- by someone else.
Happy humming, folks!