Search Songs On Google By Humming, Whistling The Song! How Does It work?

“We’ve all had that experience of having a tune stuck in our head, but can’t quite remember the lyrics. Now, when those moments arise, you just have to hum to search, and our AI models can match the melody to the right song,” read Google’s new blog post.

On October 15, Google rolled out the new feature ‘hum to search’ which helps you search for a song by singing or humming or whistling the melody, “no lyrics, artist name or perfect pitch required”. 

Read on to know more about this feature…

How To Use ‘Hum To Search’?

The ‘Hum to Search’ is currently available both on iOS and Android. It is available in English on iOS, and in more than 20 languages on Android.

On Google App or Google Widget

1. On your mobile device, open the latest version of the Google app or find your Google Search widget.
2. Tap the mic icon and say “what’s this song?” or click the “Search a song” button. 
3. Then start humming for 10-15 seconds

On Google Assistant

1. Say “Hey Google, what’s this song?”
2. Then hum the tune.

After doing the above steps, Google will show you the songs which come closest based on a percentage match score. Then you can select the best match to the song you were humming.

How Does ‘Hum To search’ Work!

The machine learning algorithm helps identify possible song matches.

Another Google blog post read, “An easy way to explain it is that a song’s melody is 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’.”

The algorithm converts the audio input into a number-based sequence. Then Google matches this number sequence to those of other song melodies and tries to find the closest one. 

“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,” the post explained.

Google says the model is trained with several sources with actual people singing, humming, and whistling in addition to real studio recordings. 

This builds on the work of Google’s AI Research team’s music recognition technology, said Google.