Difference between revisions of "Music"
m (→MusicLM | Google) |
m (→MusicLM | Google) |
||
| Line 50: | Line 50: | ||
* [https://google-research.github.io/seanet/musiclm/examples/ MusicLM: Generating Music From Text | A. Agostinelli, T. Denk, Z. Borsos, J. Engel, M. Verzetti, A. Caillon, Q. Huang, A. Jansen, A. Roberts, M. Tagliasacchi, M. Sharifi, N. Zeghidour, &C. Frank - [[Google]] Research] | * [https://google-research.github.io/seanet/musiclm/examples/ MusicLM: Generating Music From Text | A. Agostinelli, T. Denk, Z. Borsos, J. Engel, M. Verzetti, A. Caillon, Q. Huang, A. Jansen, A. Roberts, M. Tagliasacchi, M. Sharifi, N. Zeghidour, &C. Frank - [[Google]] Research] | ||
* [https://www.theverge.com/2023/1/28/23574573/google-musiclm-text-to-music-ai Google’s new AI turns text into music | Mitchell Clark - The Verge] | * [https://www.theverge.com/2023/1/28/23574573/google-musiclm-text-to-music-ai Google’s new AI turns text into music | Mitchell Clark - The Verge] | ||
| + | |||
| + | |||
| + | Google also shows off MusicLM's "long generation" (creating five-minute music clips from a simple prompt), "story mode" (which takes a sequence of text prompts and turns it into a morphing series of musical tunes), "text and melody conditioning" (which takes a human humming or whistling audio input and changes it to match the style laid out in a prompt), and generating music that matches the mood of image captions. [https://arstechnica.com/information-technology/2023/01/googles-new-ai-model-creates-songs-from-text-descriptions-of-moods-sounds/ MusicLM: Google AI generates music in various genres at 24 kHz | Benj Edwards - Ars Technica] | ||
| + | |||
| + | <hr> | ||
| + | |||
| + | Slow tempo, bass-and-drums-led reggae song. Sustained electric guitar. High-pitched bongos with ringing tones. Vocals are relaxed with a laid-back feel, very expressive. | ||
| + | |||
| + | <hr> | ||
<img src="https://duet-cdn.vox-cdn.com/thumbor/0x0:2158x592/828x227/filters:focal(1079x296:1080x297):format(webp)/cdn.vox-cdn.com/uploads/chorus_asset/file/24391491/Screenshot_2023_01_27_at_15.17.40.png" width="1100"> | <img src="https://duet-cdn.vox-cdn.com/thumbor/0x0:2158x592/828x227/filters:focal(1079x296:1080x297):format(webp)/cdn.vox-cdn.com/uploads/chorus_asset/file/24391491/Screenshot_2023_01_27_at_15.17.40.png" width="1100"> | ||
Revision as of 11:32, 19 February 2023
Youtube search... ...Google search
- Case Studies
- Capabilities
- Magenta
- Time & Music
- Maroofy ... Discover similar music you'll love
- AI could help us deconstruct why some songs just make us feel so good | Karen Hao - MIT Technology Review
- AIVA (Artificial Intelligence Virtual Artist)
- Jukedeck
- Melody Mixer: Using TensorFlow.js to Mix Melodies in the Browser | Torin Blankensmith - Medium
- AI co-produced Taryn Southern's new album | The Verge
- How AI is solving one of music’s most expensive problems | Dani Deahl
- MusicVAE: Creating a palette for musical scores with machine learning | Roberts, engel, Raffel, Simon, and Hawthorne
- Microsoft’s AI generates voices that sing in Chinese and English: Singing Voice Synthesis with Data Mined From the Web | Kyle Wiggers - VentureBeat
- Spotify Offers Personalized Artificial Intelligence Experience With The Weeknd | Gabrielle Leung - HypeBeast ...When users enter the microsite, an avatar of The Weeknd appears on screen and addresses each user by name.
- Lost Tapes of the 27 Club | Over The Bridge
MusicLM | Google
- MusicLM: Generating Music From Text | A. Agostinelli, T. Denk, Z. Borsos, J. Engel, M. Verzetti, A. Caillon, Q. Huang, A. Jansen, A. Roberts, M. Tagliasacchi, M. Sharifi, N. Zeghidour, &C. Frank - Google Research
- Google’s new AI turns text into music | Mitchell Clark - The Verge
Google also shows off MusicLM's "long generation" (creating five-minute music clips from a simple prompt), "story mode" (which takes a sequence of text prompts and turns it into a morphing series of musical tunes), "text and melody conditioning" (which takes a human humming or whistling audio input and changes it to match the style laid out in a prompt), and generating music that matches the mood of image captions. MusicLM: Google AI generates music in various genres at 24 kHz | Benj Edwards - Ars Technica
Slow tempo, bass-and-drums-led reggae song. Sustained electric guitar. High-pitched bongos with ringing tones. Vocals are relaxed with a laid-back feel, very expressive.
:format(webp)/cdn.vox-cdn.com/uploads/chorus_asset/file/24391491/Screenshot_2023_01_27_at_15.17.40.png)
Neurorack
The first deep AI based synthesizer. We developed the first musical audio synthesizer combining the power of deep generative models and the compacity of Eurorack format; comes in many formats and more specifically in the Eurorack format. The current prototype relies on the NVIDIA Jetson Nano. The goal of this project is to design the next generation of music instrument, providing a new tool for musician while enhancing the musician's creativity. It proposes a novel approach to think and compose music. We deeply think that AI can be used to achieve this quest. The Eurorack hardware and software have been developed by our team, with equal contributions from Ninon Devis, Philippe Esling and Martin Vert.
OpenAI JukeBox AI
- [htts://openai.com/blog/jukebox/ JukeBox AI]
Making Music
