×
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT

Google can now identity your earworm tune with just hum or a whistle

Last Updated 19 October 2020, 10:05 IST

Do you have an earworm, a catchy tune playing in the head, but having trouble recalling the name of the song or even the lyrics. Guess that, search engine giant Google, staying true to its caliber, has developed an advanced Artificial Intelligence (AI) machine learning model that can identify sony with just with a hum on all phones.

"When you hum a melody into Search, our machine learning models transform the audio into a number-based sequence representing the song’s melody. Our models are trained to identify songs based on a variety of sources, including humans singing, whistling, or humming, as well as studio recordings. 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," Google said.

Google can identify music with just hum or a whistle. Credit: Google.
Google can identify music with just hum or a whistle. Credit: Google.

Here's how it works on the Google search feature:
Step 1: Just open the Google app and tap on the mic icon for the phone to start audio recording by saying 'what's this song?” or click the “Search a song” button.
Step 2: Then start humming for 10-15 seconds.
Step 3: Based on the audio matching done by Google's machine learning model, it will list the most probable songs.

This feature is currently available in English on iOS, and in more than 20 languages on Android. Google says it will expand this to more languages in the coming future.

It can be noted that users can do the same with Google Assistant as well.

Once you invoke Google Assistant and say “Hey Google, what’s this song?” and then hum the tune or a whistle for 10-15 seconds.

Check out Google's video demo below:

Get the latest news on new launches, gadget reviews, apps, cybersecurity, and more on personal technology only on DH Tech.

ADVERTISEMENT
(Published 19 October 2020, 10:05 IST)

Follow us on

ADVERTISEMENT
ADVERTISEMENT