In their study, the team examined a dataset of 110 popular films released between 2014 and 2019.
Then they applied a deep learning network,which extracted auditory information such as timbre, harmony, melody, rhythm and tone from the music and score of each film. She used machine learning to analyze these musical characteristics and was able to accurately classify the genres of each film based on those characteristics alone.
Scientists have also interpreted these models toidentify which musical characteristics most indicate differences between genres. The models did not indicate which types of notes or instruments were associated with each genre, but they found that tonal and timbre characteristics are most important in predicting a film genre.
It is intuitively clear that the soundtracks of differentgenres of films use certain musical elements. Rom-coms feature rich strings and lyrical melodies, while horror films are full of disturbing, shrill frequencies and frighteningly discordant notes.
However, scientists decided to find quantitativeevidence that elements of a film's soundtrack can be used to characterize a film's genre. They were the first to apply deep learning models to a soundtrack to see if a computer could predict a movie genre based on music alone. It turned out that AI can indeed accurately classify the genre of a movie using machine learning. The study confirmed the scientists' assumption that the soundtrack of the film strongly influences the way people perceive different pictures.
To read Further
A unique boat turns into a submarine in two minutes and is invisible to the enemy
Physicists have cooled atoms to the lowest temperature in the world
The most detailed model of the Universe has been published online. Anyone can study it