Date: August 25, 2023
YouTube, the world’s biggest video content platform, is now testing a feature allowing users to find the songs they can’t remember by just humming.
We all encounter a situation where a song gets stuck in our head but just refuses to come out completely. We often solve this challenge by humming and putting our minds on a rigorous expedition into history. But most of the time, it ends up in an utter failure unless a friend identifies the song and relieves us from our anxiety. One solution that exists in the market and has been a leader in this domain is Shazam. However, the powerful app is only fully efficient on iPhones, as the app's maker is Apple itself.
But now, even Android users can use this superpower to relieve themselves from the never-ending loop of incomplete tunes running in their heads. YouTube, the largest video content platform in the world, is testing a voice search feature that will let its application users find a song just by humming its melody.
According to Google's support page, it has initiated the trials on limited Android versions. The users with access to the trial version can switch from regular search to humming the song instead. Not only this, users can hum, sing, or record audio from another device for three seconds to start getting results.
YouTube then identifies the audio and shows results in the form of official videos, user-generated versions, and shorts. This capability is not new to YouTube. Google, the platform's parent company, has tested this capability across its three products using the microphone icon: Google App, Google Search Widget, and Google Assistant. This feature allowed users to sing, hum, or even whistle the melody to get their desired results.
A comparative performance analysis revealed YouTube’s prowess over its competitors during the test. Users have to hum for a duration of up to 15 seconds to get the most accurate results. But this test feature gave better results than Apple's Shazam and Siri. Apple services require a user to record a portion of the song to get the desired result.
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!
Considering the excellence portrayed by the test feature, the commercial version has a high probability of capturing the Android user market over Shazam. However, considering the loyalty of Apple users, Shazam will likely retain its user base unless the contrast in performance is quite evident.
In May 2023, Google rolled out an AI tool called MusicLM to generate high-fidelity music from text and humming prompts. Considering the advancement it is working on, we might see a flagship product coming soon aligned with the full-blown feature of humming songs to either get results or create your own song.
By Arpit Dubey
Arpit is a dreamer, wanderer, and tech nerd who loves to jot down tech musings and updates. With a knack for crafting compelling narratives, Arpit has a sharp specialization in everything: from Predictive Analytics to Game Development, along with artificial intelligence (AI), Cloud Computing, IoT, and let’s not forget SaaS, healthcare, and more. Arpit crafts content that’s as strategic as it is compelling. With a Logician's mind, he is always chasing sunrises and tech advancements while secretly preparing for the robot uprising.
OpenAI Is Building an Audio-First AI Model And It Wants to Put It in Your Pocket
New real-time audio model targeted for Q1 2026 alongside consumer device ambitions.
Nvidia in Advanced Talks to Acquire Israel's AI21 Labs for Up to $3 Billion
Deal would mark chipmaker's fourth major Israeli acquisition and signal shifting dynamics in enterprise AI.
Nvidia Finalizes $5 Billion Stake in Intel after FTC approval
The deal marks a significant lifeline for Intel and signals a new era of collaboration between two of America's most powerful chipmakers.
Manus Changed How AI Agents Work. Now It's Coming to 3 Billion Meta Users
The social media giant's purchase of the Singapore-based firm marks its third-largest acquisition ever, as the race for AI dominance intensifies.