😫Tomorrow night, "Acapopella" - my whisper audio-visual experiment will premiere as part of
@siggraph New Media Architectures projection show the Daniels & Fisher Clock Tower in Denver. It is the first sketch of my new music series inspired by studies of supernormal stimuli and generative AI.
This year, I've been experimenting AI Audio To Audio with my sound and music creations, integrating it into my audio fx chain and my own DSPs, resulting in many unexpected auditory experiences and structures. I trained a speech model with a large amount of human moanings and growls, to inter-convert between synthesizer tones and human voices. Through multiple resampling and collages, the sounds ensemble similar to Acapella, retaining some original rhythms and melodies, while deriving similar clips from the same sound pattern, creating a bizarre auditory experience intersects synthesizer and groaning screams.
The visual involves my own photos and the faces of various other species to generate the final result. Within the constantly changing images under the same pattern—who am I? What distorts my self-perception?—the original appearance is blurred to the point of uncertainty, forming an weird landscape together with the sound.
#AudioVisual #SIGGRAPH #AI #Music #Sound #AudioToAudio #SpeechToSpeech