YouTube’s New Feature: Just hum a song and find it in seconds

Searching for songs became easier at that time due to youtube new update at music category.

Google announced last week that it will start testing a brand new feature that will allow Android users to search for songs on YouTube through just humming or singing.

“We’re experimenting with people with the ability to find a song on YouTube so they can sing or record a song that’s currently being played,” said a statement on YouTube’s support page.

According to the page, people who are in the beta group can toggle the new feature from YouTube’s voice search and we can record the song you are searching for for 3 or more seconds. ‘

Once the song is identified by the software, the video sharing website will send the user all relevant official music content, user-generated videos, and/or shorts featuring songs searched in the YouTube app.

The Google-owned company says that although only a small portion of Android users currently have this feature, a new update will soon be released for everyone.

If the update proves successful, the new feature will put YouTube in direct competition with Apple-owned app Shazam.

According to Google, their goal is twofold: one is to “make it easier for users to find content on YouTube”, while the other is to reduce the pressure put on creators to upload multiple times a day.

Aatac Unal/Anadolu Agency/Getty Images

This is not the first time Google has integrated Sound to Search technology into one of its platforms.

In 2020, the technology giant reportedly launched the feature on the Google app, Google Search Widget and Google Assistant.

Getty Images/iStockphoto

However, the key difference is that users have to echo the tune for 10 to 15 seconds instead of three.

“When you echo a tune in a search, our machine learning models convert the audio to a number-based sequence representing the song’s melody,” the search engine explained. “Our models are trained to identify songs based on a variety of sources, including human singing, whistling or humming, as well as studio recordings.

The algorithm also removes all other details, such as the timbre and accent of the accompanying devices and sound. We are left with the number-based layout or fingerprint of the song.

‎”We compare these sequences to thousands of songs around the world and identify potential matches in real time.‎

Leave a Reply

Your email address will not be published. Required fields are marked *