DeepMind发布了Lyria 2音乐生成模型

DeepMind发布了Lyria 2音乐生成模型
DeepMind releases Lyria 2 music generation model

原始链接: https://deepmind.google/discover/blog/music-ai-sandbox-now-with-new-features-and-broader-access/

音乐AI沙盒和Lyria 2是Google DeepMind和Alphabet团队合作开发的项目。 **音乐AI沙盒开发者：** Adam Roberts, Amy Stuart, Ari Troper, Beat Gfeller, Chris Deaner, Chris Reardon, Colin McArdell, DY Kim, Ethan Manilow, Felix Riedel, George Brower, Hema Manickavasagam, Jeff Chang, Jesse Engel, Michael Chang, Moon Park, Pawel Wluka, Reed Enger, Ross Cairns, Sage Stevens, Tom Jenkins, Tom Hume, Yotam Mann, Arathi Sethumadhavan, Brian McWilliams, Cătălina Cangea, Doug Fritz, Drew Jaegle, Eleni Shaw, Jessi Liang, Kazuya Kawakami 和 Veronika Goldberg。 **Lyria 2 开发者：** Asahi Ushio, Beat Gfeller, Brian McWilliams, Kazuya Kawakami, Keyang Xu, Matej Kastelic, Mauro Verzetti, Myriam Hamed Torres, Ondrej Skopek, Pavel Khrushkov, Pen Li, Tobenna Peter Igwe, Zalan Borsos, Adam Roberts, Andrea Agostinelli, Benigno Uria, Carrie Zhang, Chris Deaner, Colin McArdell, Eleni Shaw, Ethan Manilow, Hongliang Fei, Jason Baldridge, Jesse Engel, Li Li, Luyu Wang, Mauricio Zuluaga, Noah Constant, Ruba Haroun, Tayniat Khan, Volodymyr Mnih, Yan Wu 和 Zoe Ashwood。 Aäron van den Oord, Douglas Eck, Eli Collins, Mira Lane, Koray Kavukcuoglu和Demis Hassabis提供了关键指导和支持。 Google DeepMind和Alphabet的众多个人也做出了额外贡献，其中包括由Vivien Lewit领导的YouTube艺术家合作团队。

DeepMind发布了最新的AI音乐生成模型Lyria 2，在Hacker News上引发了热议。这一发布激起了关于AI在创意领域作用的争论，一些用户担心AI生成的内容会贬低人类艺术创作的价值，并可能取代音乐家。也有人质疑这是否只是一个真正可用的产品，而不是谷歌式的自我吹嘘。然而，另一些人则认为AI是一种赋能工具，允许人们无论技能水平如何都能进行音乐表达。评论者们就AI对音乐创作的影响、人机合作在音乐制作中的可能性及其在个人表达和娱乐方面的潜力（例如创作个性化的diss track或独特的背景音乐）展开了辩论。也有人担心这是音乐行业开始走向低俗化，以及创造力作为一种真正艺术形式的丧失的开始。最终，一个核心矛盾出现了：AI应该优先自动化琐碎的任务以释放人类的创造力，还是应该专注于创造性自动化，这可能会降低人类艺术技能的价值？

（评论） 2024-09-06

与AI共同科学家一起加速科学突破 2025-02-21

谷歌在人工智能的各个方面都占据优势 2025-04-12

AudioX：用于任何内容到音频生成的扩散变换器 2025-04-14

原文

Music AI Sandbox was developed by Adam Roberts, Amy Stuart, Ari Troper, Beat Gfeller, Chris Deaner, Chris Reardon, Colin McArdell, DY Kim, Ethan Manilow, Felix Riedel, George Brower, Hema Manickavasagam, Jeff Chang, Jesse Engel, Michael Chang, Moon Park, Pawel Wluka, Reed Enger, Ross Cairns, Sage Stevens, Tom Jenkins, Tom Hume and Yotam Mann. Additional contributions provided by Arathi Sethumadhavan, Brian McWilliams, Cătălina Cangea, Doug Fritz, Drew Jaegle, Eleni Shaw, Jessi Liang, Kazuya Kawakami, and Veronika Goldberg.

Lyria 2 was developed by Asahi Ushio, Beat Gfeller, Brian McWilliams, Kazuya Kawakami, Keyang Xu, Matej Kastelic, Mauro Verzetti, Myriam Hamed Torres, Ondrej Skopek, Pavel Khrushkov, Pen Li, Tobenna Peter Igwe and Zalan Borsos. Additional contributions provided by Adam Roberts, Andrea Agostinelli, Benigno Uria, Carrie Zhang, Chris Deaner, Colin McArdell, Eleni Shaw, Ethan Manilow, Hongliang Fei, Jason Baldridge, Jesse Engel, Li Li, Luyu Wang, Mauricio Zuluaga, Noah Constant, Ruba Haroun, Tayniat Khan, Volodymyr Mnih, Yan Wu and Zoe Ashwood.

Special thanks to Aäron van den Oord, Douglas Eck, Eli Collins, Mira Lane, Koray Kavukcuoglu and Demis Hassabis for their insightful guidance and support throughout the development process.

We also acknowledge the many other individuals who contributed across Google DeepMind and Alphabet, including our colleagues at YouTube (a particular shout out to the YouTube Artist Partnerships team led by Vivien Lewit for their support partnering with the music industry).

DeepMind发布了Lyria 2音乐生成模型 DeepMind releases Lyria 2 music generation model

DeepMind发布了Lyria 2音乐生成模型
DeepMind releases Lyria 2 music generation model