Music Identification Apps may seem magical at first, but under the hood is an advanced algorithm that can find songs in an instant. Here's how they work.
The Magic of Music Identification
It has probably happened to all of us. You dine in a nice restaurant, hang out in a coffee shop or walk around in a shop, while suddenly you hear a great song playing through the speakers. Maybe it's a song you've listened to before or a song you've never heard before. So you take out your phone, open Shazam and hold your device to the ceiling. In an instant the app tells you what the song is, who the artist is and where you can stream it.
They are fast, remarkably accurate, and can identify even the most obscure numbers. In a nutshell: they isolate the song from a recording and search it through an extensive database of tracks. But the technology behind the way they do this is quite complex and impressive.
It may shock you to know that the Shazam app we know today was released back in 2002, and the system was just as accurate and fast as it is now. All of that is thanks to a unique algorithm that would revolutionize the music world.
It's Not Just the Lyrics
At first glance, music identification apps like Shazam may seem simple. You might think they just listen to the lyrics, just like any voice assistant, and search it through a song database to tell you what the song is.
However, most music identification apps can tell you the title of an instrumental, or even the lead singer of a cover song. That's because instead of analyzing the song's lyrics, they're looking for 'fingerprints' that are unique to each song in their extensive databases.
RELATED: How to View Lyrics on an iPhone, iPad, Mac or Apple TV
You probably have devices that can be unlocked with your fingerprint, which is the arrangement of the small lines on your finger that are unique to you. Likewise, when you hold up your microphone to record a short clip of a song, this clip is converted into data patterns that Shazam or another app can look up in their database.
At first glance, this method seems prone to various problems. Most of the time, you hear music in public, there is background noise and distortion caused by the speakers, which can prevent tracks from being identified or cause inaccurate matches. A lot of data is also captured in even a short sound clip, which can make searching for these patterns in a database of millions of songs slow.
In an interview with Scientific American in 2003, Avery Li-Chun Wang, the Chief Data Scientist and co-founder of Shazam, explains how their algorithm solves these problems. The information from an audio clip can be visualized with a 3D chart known as a spectrogram, which represents a change in frequencies over a period of time. It also takes into account the amplitude, which is how loud a sound is. This is shown in a spectrogram using the intensity of color.
In the same way that people cannot perceive sound unless they have a certain frequency, instead of taking the full song into account when performing a search , Shazam only takes & # 39; peaks & # 39; which is the highest energy content in an audio clip. The fingerprints it captures occupy only the highest frequency points within a given time frame, then the peak amplitude points within those frequencies.
In a research paper for Columbia University, Wang stated that the method allows them to eliminate most of the unnecessary parts of an audio clip such as background noise and distortion. It also makes prints so small that it takes just milliseconds to identify a number in their huge database.
Shazam & # 39; s Impact
In addition to being useful to average listeners who hear a song they like, music identification apps also help shape the music world.
Radio stations and streaming services often use the data on what people share most often to find out which songs are listened to by the audience. This is useful because it indicates the catchiness and potential popularity of a song, regardless of the artist. When you identify a number with the app, you immediately see how many people have tried to identify it.
Since the emergence of Shazam, a handful of competitors have also emerged. up. Soundhound claims to be able to identify a song by simply singing or humming it, with mixed results. There is also a number identification integrated with voice apps like Google Assistant that work very similar to Shazam's system.
RELATED: The Best Free Music Streaming Sites