Ähnlich habe ich in meinem Cello-Stück „The Wires“ im Mittelteil Schallplattenspieler inszeniert.
(via kfm)

Ähnlich habe ich in meinem Cello-Stück „The Wires“ im Mittelteil Schallplattenspieler inszeniert.
(via kfm)
Rauchen schadet der Privatsphäre.
![]()
American artist Heather Dewey-Hagborg walked the streets of New York picking up cigarettes and hair for her project called Stranger Visions.
She then analysed the DNA to work out the gender and ethnicity of the people involved as well as their likely eye colour and other traits including the size of their nose, before using face-generating software and a 3D printer to create a series of speculative portraits.
https://www.standard.co.uk/go/london/arts/dna-from-cigarette-butts-wellcome-collection-exhibition-a4149521.html?fbclid=IwAR2vqO7I9lrj3NEnZkiP_m8A9U9_Br8VW6OVCynIziG2eOAKnH5ft1mu-88
(via Standard)

Signal processing engineer Stéphane Pigeon created this captivating Gregorian chant generator. It enables you to simply „conduct,“ mix, and process the sacred a cappella songs heard in the monasteries of the Roman Catholic Church since the 9th century.
Samt Roboter-Mönchsingern. Möge Gott die Gebete erhören.
https://mynoise.net/NoiseMachines/gregorianChoirGenerator.php
(via BoingBoing)
Derzeit hängt’s im Maschinenraum des Blogs. Lösung kommt in den nächsten Tagen…
Danke für den Tipp, Korbinian!
Bizarres Unterfangen: Im Projekt Speech2Face: Learning the Face Behind a Voice lernt ein Neural Network Gesichtsassoziationen nach Stimmen und konstruiert schließlich Gesichter nach Sprachaufnahmen. Funktioniert immerhin schon recht gut nach Hautfarbe, Geschlecht und Alter.
How much can we infer about a person’s looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of faces and speech in Internet videos, without the need to model attributes explicitly. We evaluate and numerically quantify how–and in what manner–our Speech2Face reconstructions, obtained directly from audio, resemble the true face images of the speakers.
Man kann sich ausmalen, wie in totalitären Staaten damit Minderheiten am Telefon identifiziert werden können. Rassistische Gehörbildung, sozusagen.
(via Nerdcore)