YouTube working on tech that will identify songs by user humming

With the new feature, users only need to hum three seconds of a song before YouTube will identify it.

  Silhouettes of laptop and mobile device users are seen next to a screen projection of the YouTube logo in this picture illustration taken March 28, 2018.  (photo credit: REUTERS/DADO RUVIC/ILLUSTRATION/FILE PHOTO)
Silhouettes of laptop and mobile device users are seen next to a screen projection of the YouTube logo in this picture illustration taken March 28, 2018.
(photo credit: REUTERS/DADO RUVIC/ILLUSTRATION/FILE PHOTO)

Having a song stuck in your head without being able to remember the exact lyrics, name or artist is a common issue, which is why YouTube is working on technology that will identify a song by users humming the tune, Google Support announced on August 22.

"We’re experimenting with the ability for folks to search for a song on YouTube by humming or recording a song that’s currently being played," Google support wrote.

"If you’re in the experiment, you can toggle from YouTube voice search to the new song search feature, and hum or record the song you’re searching for for 3+ seconds in order for the song to be identified. Once the song is identified, you’ll be sent to relevant official music content, user-generated videos, and/or Shorts featuring the searched song in the YouTube app."

"This experiment is rolling out to a small percentage of people across the globe who watch YouTube on Android devices."

YouTube Kids launches in Israel, Oct. 2020 (credit: Courtesy)
YouTube Kids launches in Israel, Oct. 2020 (credit: Courtesy)

Improving old technology

Similar technology is currently being used by Shazam, an app that identifies songs after recording a short piece of it, but Shazam cannot identify songs by user interaction. Google Search and Google Assist also produced this feature in 2020 but YouTube's version is expected to be a significant improvement, with users needing to hum only three seconds instead of the 10 seconds required by the older versions.