AI in music, examples of augmented reality

Andy, why don’t you make me a machine that tunes me?’ When asked the question by the wife of a major distributor of music technology products at the 1995 Hum Show, Dr. Andy Hildebrand thought to himself: What a stupid idea. In all the years he spent at Exxon applying digital signal processing to geophysics to locate oil deposits, the American engineer never thought to hear the human voice delivering the discourse. Eight months and several equations later, he granted the woman’s wish and his algorithm, presented the following year at the same fair, was a hit. The woman never soared on the charts with a hit that accentuated her “enhanced” singing prowess, but when a rendition by Cher resonated mightily in the ether a few years later, she Do you believe in life after love With peculiar robotic diphthongs and vowels, Hildebrand’s Auto-Tune, software able to guarantee perfect re-tone, quickly switched to autotune in all lower case, marking a global and democratic innovation. Soon it is sure to become enemy number one of the people.

The manipulation of the human voice in music was not exactly new. From the late 60s onwards, soundscapes were played that contained real and unreal apocryphal fairy tales and otherworldly nightmares. With the vocoder, a device that synthesizes the voice so that it can be discovered, Neil Young trans (1982) created an alternate dimension in which the Machine became the potential voice of people with severe neurological conditions, such as his son Ben. With the talk box, a prosthetic larynx that literally tries to “talk an instrument”, Stevie Wonder or Pete Townsend of The Who created new textures. And, again, “amazing special effects” have become stylistic codes of various Kraftwerk, Daft Punk, Aphex Twin, always hovering between dystopia and futurism. Auto-Tune (along with its cousins ​​Melodyne and Waves Tune), however, has presented itself more like handbag makeup: occasionally useful for compositional corrections (see Pink Floyd, Radiohead, James Blake) but touch-ups. Always necessary for newspapers. A beauty potion that hides a flaw or an unripe talent, the scalpel of a good plastic surgeon that files and smoothes. Many have used it and are using it in the name of perfection even without a real need: Alicia Keys, Rihanna, Taylor Swift, Sia, Billie Eilish, Celine Dion, singer-songwriter Neko Case, among those fueling anger, claiming that singing is work and that more time should be spent on a few notes in the studio than on working and promoting technique. Then came the trap.

AI images by Federica di Cataldo and Tommaso Garner

/Imagine: A shot of a woman looking straight into the camera, combining the features of John Lennon and Rafaela Cara, in the style of Martin Schoeller, in high definition, ultra-realistic, with a clear background.AI images by Federica di Cataldo and Tommaso Garner

Federica de Cataldo / Tommaso Garner

Filter upon filter, the rhymes become gelatinous and cold, in self-cancellation of monochord syllables like notification sounds.

We must know that to avoid ghostly Blue (Da Ba Dee) by Eiffel 65, the sequel to Da Ba Dee Da Ba Dee is dangerously similar in sound to Super Mario Bros., quoting Ivan Karozzi age of the tiger, “There will come a not too distant future in which technology will trigger a wave of massive stupidity and cognitive impairment.” That we will collectively lose our voice. The Trapper’s Invasion – with that tee that deprives the soul, a style of rap in which words are weapons – delivers the coup de grace, complete with Frankenstein face tattoos, double Rolexes and designer sneakers. Filter by filter, his rhymes liquefy, become gelatinous and cold, taking on a sinister appeal, in a self-cancellation composed of rhythmic syllables, notification sounds like monochords, akin to garlands of receipts from luxury shopping malls. For stories of social liberation, for stories to be told. The excess of Autotune anesthetizes that without a filter it is difficult to recognize the various Sfera Ebbasta, Ghali, Drefgold and a Capo Plaza or an Izy, which achieves unplugged roundness and personality, without leaving everything unanswered Raises questions assigned to a Gen Z soccer game against Boomer. Where the latter always seems unable to understand the revolution. For some, indeed, “the digitally manipulated voice is the new vehicle of glory”. Keith McIntosh, author of Auto Tune Principle. Trap, Drill, Bashment and the Future of Music, convinced that autotuned vocal psychedelia achieves overcoming the human frame and its limitations. In a present dominated by science fiction for video games, TV series, and movies, life and the future become a two-dimensional nebula to navigate as a level God of war, Vybz Kartel, the controversial Jamaican dancehall artist, is the perfect expression of this: a self-centered lust for revenge sadly leads him to subvert and overcome the human-machine combination, to rebuild himself into a kind of divinity. For, a Meta-Man with heightened emotions needs a Meta-Voice, to reduce enemies to ashes with blows Dissing, A post-human who radiates a sense of disorientation and fears no adversaries, but deep down fears himself. More than a revolution, it seems to be an expression of a greater disquiet. The future is unknown, requiring a sort of mass exorcism. But the more it appears as a chorus of evil algorithms singing “good morning” to our favorite tune, the more salvation comes from the narrative power of mundane voices. Like Tom Waits, which smells of aged leather, sandpaper, grainy canvas, which multiplies into a myriad of sloppy characters, exuding impermanence and being affected by life and time, wine and cigarettes. that shapes and animates each character, whether it’s the blasphemer who prefers “Chocolate Jesus” to Sunday Mass, the Minneapolis prostitute who writes a cryptic letter to this Charlie or the explorers of Wonderlands turned . More meta-human than any trap device, on the other hand, is Cigarettes After Sex’s Greg Gonzalez’s voice, which dissolves the baritone tone of the singing speech into a lighter, almost feminine timbre, like a black A rebellious diva white noir. Or the very delicate one of Arlo Parks, which – every note of the new work says, my cool machine – asserts itself through the sound of space, parted lips that emphasize dialectal consonants, imperceptible constrictions that accentuate fragility. And they suggest: you live now, in the present that feeds on nuances. Get used to choosing them again.

It’s the bare voice that befits a real superhero. Be it a Grace Jones, a Jeff Buckley, an Ella Fitzgerald, a Chris Cornell or an Amy Winehouse featuring you, that defines you even when no one knows your face. It is an instrument that, regardless of the octaves covered by it or the perfect pitch, can affirm, deny, explain, solicit, evoke reactions and feelings, spell can generate. Advent, as demonstrated by Demetrio Stratos in triplophony, diplophony, flutophony, and the real world singing voice, where no filter or fix can take it. A naked voice, today, is a reappropriation of the self that doesn’t battle and victimize too-young TikTokers with synthetic catchphrases or ghost sunglasses that crossbreed Drake and The Weeknd’s voices to create AI hybrids . When T-Pain, one of the patron saints of Autotune, decides to trash the requests of the mask and the market and record an album of covers releasing a soulful time-filled gospel roots take from the Southern Baptists of the United States does, one certainty becomes reality: Patti-Vocal Tees is the real revolution.

(translate to tag) ai in music

Source link

Leave a Comment