Despite the many AI platforms that offer avenues for automatically generating working music, many artists who have openly worked with AI have approached the concept in more individual ways.
Take Holly Herndon, the Berlin-based composer and musicologist who recently created her own clever musical accomplice. Dubbed “Spawn”, this vocal sample generator was taught by Herndon and his partner Mat Dryhurst to reproduce a bank of vocal types (including his own) via months of training his complex neural network. Spawn was able to organically add vocals to the tracks presented to him.
Although, as Herndon said Art in Americathe process is still finding its feet: “The AI isn’t that smart, it’s very infidel, it’s not real-time, it’s very slow and unwieldy. Spawn can take longer 24 hours to process someone’s voice input. On the other hand, it has some unique abilities that are quite exciting and scary. The AI can extract logic from something outside of its own logic. operator and recreate it. This is entirely new to music computing.
A virtual colleague
Herndon’s approach – subverting the often predictable creative choices of the human musician and opening up new avenues of musical exploration – is a commonality shared by many artists who have worked with AI. Alex Da Kid’s “collaboration” with IBM’s Watson was sparked by the Grammy-winning producer’s interest in whether it was actually possible to make a song with a virtual colleague.
Watson uses an accumulation of data collected by a network of intelligent APIs. These include Watson Alchemy Language, which studies five years of media to determine current pop cultural themes, Watson Tone Analyzer, which has also analyzed approximately 26,000 lyrics, and, most importantly, Watson Beat, which determines the best chords, tones and frames to match a certain theme. With the track Not easy, the couple explored the theme of heartbreak – and produced a stunning statement, which also saw interjections from Wiz Khalifa, Elle King and the X Ambassadors. The brilliant end result was popular enough to top the iTunes and Spotify charts.
While Alex and Holly’s involvement in AI was driven by a desire to research the potential of AI, amazing YouTube star Taryn Southern I am AI LP was conceived when the singer-songwriter was struggling to realize the musical ideas she had in mind. Using a combination of AI music generators Amper Music and Aiva as well as Google’s Magenta and IBM Watson, Taryn has created a new music toolkit to work with. As Southern said Digital trendshis approach was to use the fine-tuning tools of software like Amper to deviate from his original ideas, download the stems, and then rearrange the final results in his DAW.
These artists, each venturing further down the AI hole, albeit in different ways, are at the forefront of a new paradigm for creators. It’s almost a matter of “when” as opposed to “if” AI will stop being seen as an industry buzzword and become an everyday facet of music creation. Through their work, these artists are laying the groundwork for the successful absorption of AI into the creative process.
learn to fly
While these examples only scratch the surface of how AI has been applied by artists in various genres and contexts (see our list of ten AI-built records), in other areas AI has already fully begun to inform our daily lives.
He is fully immersed in How? ‘Or’ What we listen to our music. Streaming platforms and ubiquitous music listening services have algorithms that intelligently serve up tracks similar to those we play regularly, creating intelligently curated playlists based on data reported by our listening habits.
Spotify’s “Discover Weekly” smart playlists were designed in collaboration with French artificial intelligence startup Niland. This intelligent neural network determines the best way to populate these lists by scanning other users’ playlists that feature these tracks, as well as analyzing the tracks’ waveforms to determine musicological similarities. “We’re working on a number of ways to elevate the experience even further.”
Spotify’s head of research, Rishabh Mehrotra, explained to AI News“Reinforcement learning will be an important focal point as we look for ways to optimize for a lifetime of fulfilling content, rather than optimizing for the next stream. In a sense, it’s not about to give users what they want now rather than evolving their tastes and looking at their long-term trajectories.
Do not be afraid
We will take the liberty of circumventing the many prophecies of doom heralded by those who fear AI encroachment on their financial turf. Consider instead the alternative, while online AI platforms can easily create the kind of utility music that accompanies a simple YouTube video or podcast, for real soundtrack requirements real human composers will certainly be needed. .
The feeling, the heart, the soul and also the “story” of the soundtrack process are all essential to modern film, television and video game soundtracks. Also in terms of production, there is so much that AI can add to, rather than take away from, the modern producer’s workflow. “Will AI remove all mixing jobs? Absolutely not,” says Alexander Wankhammer, CMO of Sonible.
“Will it change the way the industry works in certain areas? Definitely yes. I think people shouldn’t be afraid of the new possibilities that AI is creating – they should stay curious and see AI as a really exciting new tool that will (to some degree) shape the future of music production.
10 recordings that use AI
1. Outside – David Bowie (1995)
While not strictly speaking AI in the modern sense, Bowie’s use of Verbasizer software to concoct new lyrical ideas was something of a digital continuation of the random “slicing” technique on which he had relied for his earlier works. Many Pieces of Bowie’s Hidden Gem Outside were mapped from these computer-suggested ideas.
2. Not Easy – Alex Da Kid (2016)
A collaboration between Dr. Dre and Eminem producer Alex Da Kid and IBM’s cultural learning and idea-creating digital intelligence, Watson. Said to investigate the theme of “grief”, Watson provided Alex with a suitable rhythmic, lyrical and chordal basis. The stunning results also featured Wiz Khalifa, Elle King and the X Ambassadors.
3. Return 0 – Ash Koosha (2018)
Created by Iranian composer Ash Koosha in collaboration with artificial intelligence Yona, Back 0 is a sometimes beautiful, sometimes stimulating work that emphasizes its innovative vanity in its futuristic arrangements. Able to generate melodic sequences and even his own lyrics and vocals, we can’t wait to see what Yona does next.
4. Smartbeats – Toro Y Moi (2019)
Built in tandem with commercially available AI soundscape designer Endel, American producer and songwriter Toro Y Moi has built a four-track series to promote Glaceau Smartwater. The smart beats EP contains the quiet, emotional fruits of his labors – and those of his virtual assistant.
5. Holly Herndon – Proto (2019)
Harnessing ‘Spawn’, Herndon’s self-trained AI voice generator, Proto’The fusion of character artistic sensibilities of Herndon and Spawn twisting and breaking the rules makes for a captivating listen. Its glitchy, computerized textures battle Holly’s creative personality in fascinating ways, ultimately leading to the sonic equivalent of the two merging.
6. Shadow Planet – The Modules of Cotton (2021)
Examining the space between human composition and AI-powered arrangements, the debut of Oakland-based duo The Cotton Modules is a remarkable listen. In collaboration with machine learning maker Jukebox, the disc swims in evolving, ambient textures and loops. In making the record, the duo came to see this other sensibility as an instrument they needed to learn to work with.
7. Hello World – SHADOW (2018)
Benoit Carré presented Sony CSL’s Flow Machines with ideas, which the AI then developed. He took that and made a solid pop record. Rather than a neural network, Flow Machines used “Markov chains,” probability equation generators that require less data to operate.
8. I am AI – Taryn Southern (2018)
Perhaps the most publicized AI-built record on the list. YouTube superstar Taryn Southern’s eight-track LP was built with music composition tuner Amper. Southern’s work received wide press.
9. The Lost Tapes – The 27 Club (2021)
An original idea, to encourage musicians to speak openly about mental health. The 27 Club used AI to create new tracks, based on the music of these famous and influential musicians who, curiously, passed away at the age of 27. With real singers replacing deceased singers, this is the AI used for the human act of remembrance.
10. RATM Style Music Samples – AI Kittens (2021)
Like The 27 Club project, this album was created by an AI that studied the typical rap metal quartet canon structure and generated short samples, which the AI Kittens artists sculpted into sturdy guitar workouts. .