File picture
File picture

Google's new ’hum to search’ feature will help you get rid of your earworm

By Yasmine Jacobs Time of article published Oct 16, 2020

Share this article:

Cape Town - We all know how absolutely frustrating it is when you can’t remember the lyrics of a song - let alone, the name - but the tune has been stuck in your head the entire day.

Well, Google has found a solution for this. The company has announced that Google can now help you figure out the name of the song that has been bothering you and no lyrics, artist name or perfect pitch are required.

You can now hum, whistle or sing a melody to Google to solve your earworm.

This is how to do it:

On your phone, open the latest version of the Google app or find your Google Search widget.

Tap the mic icon and say “what's this song?” or click the “Search a song” button.

Start humming for 10-15 seconds.

On Google Assistant, say “Hey Google, what’s this song?” and then hum the tune.

This feature is currently available in English on iOS, and in more than 20 languages on Android. And we hope to expand this to more languages in the future.

“After you’re finished humming, our machine learning algorithm helps identify potential song matches. And don’t worry, you don’t need perfect pitch to use this feature. We’ll show you the most likely options based on the tune. Then you can select the best match and explore information on the song and artist, view any accompanying music videos or listen to the song on your favorite music app, find the lyrics, read analysis and even check out other recordings of the song when available,” said Google in a blog post.

How does the hum-to-search function work?

Google described a a song’s melody like its fingerprint: They each have their own unique identity.

“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. 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.”

These sequences are compared to thousands of songs from around the world and identify potential matches in real time.


Share this article: