By Edward Cardenas
SOUTHFIELD (CBS Detroit) – Computer scientists at Lawrence Technological University used artificial intelligence to correctly track the musical progression of The Beatles.
LTU Assistant Professor Lior Shamir, and graduate student Joe George, used an audio analysis technology originally developed to study the vocal communication of whales, and expanded the algorithm to analyze the albums of the Beatles.
Die-hard fans of the Fab Four may be able to tell the difference and place songs the band recorded over the course of seven years the band was together, but could a formula?
Researchers analyzed 11 songs from each of the 13 Beatles studio albums released in Great Britain and converted each song to a spectrogram – a visual representation of the audio content – which allowed them to analyze textures, shapes and the statistical distribution of the pixels.
Pattern recognition and statistical methods were then used to detect and quantify the similarities between different pieces of music, according to university officials.
According to the study, published in the August issue of the journal Pattern Recognition Letters, found “that the structure of the Beatles music changes from one album to the next.”
“People who are not Beatles fans normally can’t tell that ‘Help!’ was recorded before ‘Rubber Soul,’ but the algorithm can,” said Shamir in a release. “This experiment demonstrates that artificial intelligence can identify the changes and progression in musical styles by ‘listening’ to popular music albums in a completely new way.”
The algorithm automatically placed the albums by the algorithm in chronological order of the recording of each album, starting with the Beatles’ first album, “Please, Please Me,” and followed by the consequent early albums, “With the Beatles,” “Beatles for Sale” and “A Hard Day’s Night.”
It also determined that songs on “Let It Be” – the last album released by the Beatles – were recorded earlier than the songs on “Abbey Road.”
These algorithms can help in searching, browsing, and organizing large music databases, as well as identifying music that matches an individual listener’s musical preferences, LTU officials state.
“The baby boomers loved the music of the Beatles, I love the Beatles, and now my daughters and their friends love the Beatles. Their music will live on for a very long time,” Shamir said. “It is worthwhile to study what makes their music so distinctive, and computer science and big data can help.”