AUDIO + AI

SUMMARY

Without a doubt, Artificial Intelligence will be present in our daily life for the next years. Machine learning is a branch of computer science that gives the AI the ability to learn. To achieve this, programmers rely on Machine Learning algorithms, the question is ... how will this affect the arts ?.

The term machine learning is often confused with that of Artificial Intelligence, when in reality it is a subfield. It is defined as the ability of the computer to learn without being explicitly programmed.

In its most basic form, machine learning uses programmed algorithms that receive and analyze input data to predict output values within an acceptable range. As new data is introduced into these algorithms, it learns and optimizes its operations to improve performance, developing "intelligence" over time.

Such is the case of Google, which recently created an experimental device called "Magenta" and is based on neural networks. The synthesizer learns the basic qualities of an instrument, then combines its sound with that of others to generate something completely different.

But this is not the only field of application, in the Laboratory of Computer Science and Artificial Intelligence of MIT, they presented some years ago an algorithm capable of "guessing" a sound from a video. The algorithm analyzes the sound properties of each frame of the video and matches them with the most similar sounds in the database. Once the system gathers those audio fragments, it assembles them and creates a coherent sound with the image automatically.

Will the end of post-production? Without a doubt, technological progress in the immediate future will allow experts in the field to have a set of tools to improve their work.

There are many applications that are worth reading.

More information at https://www.technologyreview.es (MIT Technology Review)

Nahuel Proietto