Click HERE to see this thread with all of the graphics, features, and links.

Musicians can't tell the difference!!

The definition of 'artificial creativity' involves the possibility of machines to be programmed to generate artifacts of any kind comparable with those made by a human mind, through processes and algorithms impossible for a human to reproduce manually. In classical music there exist many deep studies about the simulation of the style of a particular artist, through a painstaking analysis of his works and the individuation of certain 'patterns' which identify the seeds, rough but indicative, of the artist's style. David Cope has been involved in this studies for several years, and collected in this big tome a large mass of informations on this theme. From Mozart's experiments with dices to the mathematical algorithms of Iannis Xenakis, to the creations of choirs in the style of Bach using an expert system by Kemal Ebcioglu, to the neural nets of Dominik Hornel and Wolfram Menzel, used to create pieces similar to those composed by famous renaissance and baroque composers. The author introduces the reader to the 'game' of telling the original from the simulation, in a sort of musical 'Turing test' which, the reader is warned, has tricked almost half of the people who took it, as well as renowned musicologists with years of experience. The use of a database for creating a piece in the style of Mozart is described step by step and allows the reader to see with his own eyes the generation of plausible patterns through the use of well designed algorithms. The obvious doubts about the epistemological validity of such experiments give rise to questions on the possibility to reproduce the unconscious and the experiences, sensations and personal feelings which contribute to formally generate the pieces. It's difficult to dispel such doubts in a simple way, but the formal research towards a possible authorship of the machine involves travelling through uncharted territories which are certainly worth exploring.

Can't that be put in point form?

The musicians he chose couldn't tell, it doesn't mean musicians in general can't.

The funny thing is, that you seem to overlook, is that any music on a computer is at some point, created by humans. A computer can't play a violin or an instrument, it can't strum a guitar. If all the pieces are there, it's just composing pieces of music that humans have made and putting it together. It's not creating them.

-AC

I just see self-whooping on your part.

Anyway, no reason to continue your self-abuse in both threads.

-AC

Originally posted by Alpha Centauri
I just see self-whooping on your part.

Anyway, no reason to continue your self-abuse in both threads.

-AC

It only shows you up, please offer something other than opinion.

Lopez de Mantaras, Ramon and Josep Lluis Arcos. 2002. AI and Music: From Composition to Expressive Performance. AI Magazine 23(3): 43-58. "In this article, we first survey the three major types of computer music systems based on AI techniques: (1) compositional, (2) improvisational, and (3) performance systems. Representative examples of each type are briefly described. Then, we look in more detail at the problem of endowing the resulting performances with the expressiveness that characterizes human-generated music. This is one of the most challenging aspects of computer music that has been addressed just recently. The main problem in modeling expressiveness is to grasp the performer's 'touch,' that is, the knowledge applied when performing a score. Humans acquire it through a long process of observation and imitation. For this reason, previous approaches, based on following musical rules trying to capture interpretation knowledge, had serious limitations. An alternative approach, much closer to the observation-imitation process observed in humans, is that of directly using the interpretation knowledge implicit in examples extracted from recordings of human performers instead of trying to make explicit such knowledge. In the last part of the article, we report on a performance system, SAXEX, based on this alternative approach, that is capable of generating high-quality expressive solo performances of jazz ballads based on examples of human performers within a case-based reasoning (CBR) system."

Another hole in your arguments.

Give up AC expert evidence is against you! You have nothing.

Three threads and you've failed in all of them.

Let it go man. Google can save only so much.

-AC

Computers can be programmed to recreate, not create something that's fresh, new and from the imagination.

He doesn't understand that.

-AC

Originally posted by Alpha Centauri
He doesn't understand that.

-AC

Ehn... I'd like to hear his music

As far as I can tell, this entire debate stemmed from a misinterpretation of this post:

Originally posted by Alpha Centauri
No amount of computer technology is ever going to be as emotional or complexed as a great band, but it would be nice to see them develop.
Which I think was basically supposed to mean that live bands > DJ's/Hip Hop producers, in terms of emotion. I could be wrong though.

In any case, this article is basically an entirely different issue than the original post. Computers don't write hip hop beats, producers do.

It's not really a surprised that computers can be programmed to compose music... it all essentially breaks down to numbers. But like Gabriel said you won't have any computers "pushing the envelope" so to speak.