AI and the future of music


Last night’s 60 minutes featured a deep look at Google’s new AI program BARD. Frightening, yet compelling.

It got me thinking, if their AI has already read everything on the internet, and can create verse, stories, etc in seconds…What could it do for music?

‘Hey , BARD create a new Beatles like song from the Rubber Soul era, but have Paul Rodgers and Jack Bruce singing”.

“Hey BARD, create a song that will melt the heart of my new girlfriend”.

 

your ideas?

128x1281111art

Music is and is not mathematic... Sorry for the paradox...

Music as a written or translation of sounds by marks is mathematic..

As a playing live event, it is not...

I will say it in a more deeper way :

Mathematic is music at the end , but music is never only mathematic to begin with ..

 

Music is linked to non commutative mathematic...And because of this as all musical qualities studied in psycho-acoustic and produced by musicians or by the speaker of any language, are not reducible to sounds in the Fourier meaning window, which is a linear commutative "country", music is related in the many culture and in Europe to ethical and esthetical FREE CHOICES that reflect and depict human evolution in a non linear Non Fourier way in a time dependant domain... ( mathematic is time independant )

History of music is anything but a meaningless history...Every choices in music reflect deep meanings at ALL LEVELS of thinking..

Then A. I. will be able to create and imitate any sounds existing, musical one included... But there will be there no ethical and no esthetical reflected choices... This history will disapear under "pleasurable meaningless imitated sounds "...

Most people are unable to read music as ethical and esthetical history... The Choices of Beethoven are meaningful even philosophically for the HUMAN RACE... not for a machine...

Imitation will kill creativity...

 

«Music is a NEW mathematic who wrote itself spontaneously through the gesturing producing and receptive body »-- Anonymus African musician dancing while playing Yoruba talking drum...

 

 
 

 

 

I started a thread on Lalal.ai a while back but it didn't get any traction. That said, it's an excellent example of what can be done with music via AI. It allows you to split vocals from the rest of a track, or turn any vocal track into an instrumental, etc, and allows you to download it in lossless format. It's near perfect, and through my use, I've had great experiences:

https://www.lalal.ai/

Interesting thanks..

I never doubt that A.I. will be anything than also a great tool.. Positive and negative...

lIke nuclear energy...

or virus research ...

The problem is our societal immaturity... Too much powerful for us now...

More interesting to me,

is it repeatable?

Or is "the best" rendering a moving target?

https://forum.audiogon.com/posts/2582616
 

@mahgister 

Either you missed my point, or more likely I just didn’t articulate it well.

Music, as played by the interpretation of the artist and the inference of the listener through their “world view”, ethics and values, is not what I was trying to describe with respect to creating an “arrangement.”

Just the arrangement of the notes, in any combination, with any set timing pattern, can absolutely be mathematically derived.  As such, given sufficient processing power, storage and time, the entire universe of those arrangements can be calculated and stored and the pattern used in a copyright attempt.  Which is what I find objectionable.