more images

In the work “Parlando”, a neural network listens to the rushing of a river and recognizes fragments of human speech in it. The animistic ritual of listening to the river is taken over by a speech recognition machine. A new, independent text emerges from the flow of words, which are “read” from the sounds and noises of the water.

In the work, the limits of the AI ​​(which can only read what it hears due to its programming) are the driving force behind the artificial-poetic text creation.
By interpreting the sound of the river as a human voice, it actually becomes the text and the supposedly hidden message of the gurgling, babbling water.

spectral sound analysis, deep learning, video;