Google now lets you hum as a way to search for songs, so we tried 6 proudly SA hits

Google has added a new feature to its search app that allows music lovers to hum a song that's stuck in their heads and then use the company's machine learning algorithm to try to identify it.

The SoundSearch feature was announced over the weekend and has since been rolled out globally.

According to the senior product manager at Google Search, Krishna Kumar, the feature is available in English on iOS and in more than 20 languages on Android. It will expand with more languages in the future.

“We all know how frustrating it is when you can’t remember the name of a song or any of the words but the tune is stuck in your head,” said Kumar. “Google can now help you figure it out — no lyrics, artist name or perfect pitch required.”

Watch the video below.

According to Kumar, a song's melody is like its fingerprint and they each have their own unique identity.

When users hum a melody into search, the machine learning models transform the audio into a number-based sequence representing the song's melody. The 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,” said Kumar.

“Similarly, the machine learning models recognise the melody of the studio-recorded version of the song, which “we can use to match it with a person's hummed audio”. 

TimesLIVE put Google's hum search to the Test to see if it could pick up six SA tracks.

Here's what happened:

Master KG and Nomcebo — Jerusalema: 60% match

Babes Wodumo —  Wololo: 34% match

Johnny Clegg —  Scatterlings  of Africa: 26%

Mgarimbe — Sister Bettina: No results 

Cassper Nyovest — Doc Shebeleza: No results

Kurt Darren — Kaptein: No results for the actual song