Subscribe to Moneycontrol Pro and get 365 bonus InterMiles! Use Code: INTERMILES
you are here: HomeNewsTrends
Last Updated : Oct 17, 2020 02:08 PM IST | Source: Moneycontrol.com

Google 'hum to search' feature helps find songs you can't name; here's how it works

Hum to search feature is currently available in English on iOS, and in more than 20 languages on Android.

Representative picture
Representative picture

Google has come up with an easy fix for all those who remember the tune of their favourite songs but often struggle with the lyrics. Google 'hum to search' feature allows users to hum, sing or even whistle a song to identify the track.

Users can identify songs by opening the Google app or Google Search widget and saying “what's this song?” before humming for 10 to 15 seconds. On Google Assistant, it is just as simple. Say “Hey Google, what’s this song?” and then hum the tune.

The feature is currently available in English on iOS, and in more than 20 languages on Android, Google said in a statement, adding that more languages will be added in the future.


Google's machine learning algorithm helps identify potential song matches, it said.

"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 favourite music app, find the lyrics, read analysis and even check out other recordings of the song when available," said Krishna Kumar, Senior Product Manager, Google Search.

According to Google, a song's melody is like its fingerprint. They each have their own unique identity. So when you hum a melody into Search, the machine learning models transform the audio into a number-based sequence representing the song's melody.

"For example, if you listen to Tones and I’s “Dance Monkey,” you’ll recognize the song whether it was sung, whistled, or hummed. Similarly, our machine learning models recognize the melody of the studio-recorded version of the song, which we can use to match it with a person’s hummed audio," Kumar said.
First Published on Oct 17, 2020 02:08 pm