Innovation > Early-Stage Technology
YOUTUBE, San Bruno / YOUTUBE / 2024
Overview
Credits
Why is this work relevant for Innovation?
Generative AI has the potential to transform the future of music, offering unparalleled tools for creation and opening up a world of possibilities for artists. However, it also raises important questions about fairness and responsibility. Is it possible to create a framework that upholds the integrity and financial rights of musicians and artists in this new AI-driven landscape?
Please provide any cultural context that would help the Jury understand any cultural, national or regional nuances applicable to this work.
Despite the tremendous opportunity AI presents, we recognize it’s a quickly evolving space that presents complex challenges. One of YouTube’s greatest strengths is our strong relationships with music industry partners. We’re committed to collaborating with them as we enter this new era, critically exploring together new opportunities and developing sensible and sustainable controls, monetization and attribution frameworks. We’re still in the early stages of this work and expect that we’ll continue to evolve our approach as we learn more.
Background
The emergence of AI has brought music to the cusp of a new creative era. As a myriad of companies map out their AI approach, we want ours to be defined by partnership and responsibility. That's why we’ve been exploring the possibilities of how AI can empower creativity alongside artists, songwriters, producers and our partners while also identifying its challenges. By testing and learning, we can better understand how to enhance artist and industry opportunity and deepen fan engagement, benefiting the broader music community.
Describe the idea
Introducing Dream Track and Music AI Tools: our first early experiments exploring the potential of AI and music. Dream Track allows participants to create personalized soundtracks for YouTube Shorts in the style of participating artists. Music AI Tools empowers professional musicians to instantly bring their ideas to life, pushing the boundaries of traditional studio creation. From blending genres to transforming beats into melodies and automatically generating accompaniments from vocal tracks – it could all be possible with just a few prompts.
These innovations mark the first step in our long-term commitment to fostering responsible AI. By closely collaborating with the music industry, we'll ensure these groundbreaking tools serve and benefit the creators who inspire us all.
What were the key dates in the development process?
August 21, 2023
YouTube unveils AI principles for partnering with the music industry and responsibly embracing this quickly developing technology. Introduces the AI Incubator built from various artists, songwriters and producers.
November 16, 2023
YouTube, in collaboration with Google’s DeepMind, shares a sneak peek at our first set of AI-related music experiments created with Lyria - Dream Track for Shorts and Music AI Tools. A select group of creators are given exclusive access to Dream Track to create unique soundtracks of up to 30 seconds for their Shorts utilizing the work of 9 artists (Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan). Samples are shared of Music AI Tools transforming capabilities, including Producer/Songwriter Louis Bell building a track with just a hum.
November 16, 2023 - present
Select group of creators continue to post Shorts with hashtag #DreamTrackAI. DeepMind’s researchers continue to collaborate with YouTube’s Music AI Incubator on how generative AI can best support the creative process with responsibly designed AI Tools.
Describe the innovation/technology
Dream Track in YouTube Shorts is powered by Google DeepMind's Lyria, the most advanced music generation model to date. At this initial phase, the experiment is designed to help explore how the technology could be used to create deeper connections between artists and creators, and ultimately, their fans. By simply typing an idea into the creation prompt and selecting a participating artist that appears in the carousel, an original Shorts soundtrack featuring the AI-generated voice of that artist will be produced for the creator to use in their Short.
Our Music AI Incubator of partnering artists, songwriters and producers are helping us test, learn, gain feedback and hear ideas so that we can develop the best experiences possible for our community of artists, viewers and fans. Imagine being able to more seamlessly turn one's thoughts and ideas into music, like creating a new guitar riff just by humming it or taking a pop track you are working on and giving it a reggaeton feel. We’re developing prospective tools that could bring these possibilities to life and Music AI Incubator participants will be able to test them out later this year.
Describe the expectations/outcome
Our goal was and is to collaborate with our partners boldly and responsibly. That includes clearly communicating our intentions and principles, and demonstrating our commitment to getting early feedback. Because of the experimental nature of this program, we needed to ensure that we had extra layers of protection around the content created with our participants.
Our secondary goal was to build successful case studies that Dream Track delivers Shorts user/creator <> artist connection to help explore the potential of this product. A few notable highlights:
John Legend: “Being a part of YouTube’s Dream Track experiment is an opportunity to help shape possibilities for the future. As an artist, I am happy to have a seat at the table and I look forward to seeing what the creators dream up during this period.”
Our efforts resulted in +10% net positive conversation around these tools.
More Entries from Early-Stage Technology in Innovation
24 items
More Entries from YOUTUBE
24 items