Accoring to the Spanish company Polyphonic HMI it is able to find hit songs using artificial intelligence. The technology is already in use by the major record labels to determine if a song has a hit potential. This to make sure that music that hasn't this potential will be marketed and cause losses for the labels.
Of course the software can only determine the hit potential of a song because it calculated it with data of older hits. This means it only recognises patterns that have already been used, and I suspect it will result in -only more of the same- songs.
Polyphonic's HSS analyzes the underlying mathematical patterns in unreleased music and compares them to the patterns in recent hit songs. The new technology can isolate individual patterns in key aspects of the music that humans detect and that help determine whether or not they like a given song. For example, the dictionary describes melody as a series of notes strung together in a meaningful pattern. But determining what is "meaningful" is a very human and very subjective experience. This technology is able to detect what those melody patterns are as well as decipher patterns in other aspects of the music such as beat, harmony, pitch, octave, fullness of sound, brilliance and chord progression. |
The application can recognize hidden market trends and consumer taste patterns as they evolve over time as well as complex intricacies of recorded music only understood at very deep levels of the human consciousness. Most people can't explain why they like a certain song beyond saying they like blues, or a good beat and a strong melody. This technology can actually pinpoint what complex patterns are most attractive to a given listener or audience. Music labels are using the technology to better allocate promotion spending, accurately predict sales and anticipate the market.
You can read more about this new development here. Discuss this subject in our Audio Forum.
Source: Mi2N.com
