I wonder if musicians should be worried.

Google Research introduces MusicLM, a model that can generate high-fidelity music from text descriptions. See how MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and how it outperforms previous systems in audio quality and text description adherence. Learn more about MusicCaps, a dataset composed of 5.5k music-text pairs, and see how MusicLM can be conditioned on both text and a melody. Check out this video to see the power of MusicLM: Generating Music From Text! #GoogleResearch #MusicLM #MusicGeneration.

▼ Link(s) From Today’s Video:

An impressive new AI system from Google can generate music in any genre given a text description. But the company, fearing the risks, has no immediate plans to release it.

Called MusicLM, Google’s certainly isn’t the first generative AI system for song. There have been other attempts, including Riffusion, an AI that composes music by visualizing it, as well as Dance Diffusion, Google’s own AudioML and OpenAI’s Jukebox. But owing to technical limitations and limited training data, none have been able to produce songs particularly complex in composition or high-fidelity.

MusicLM is perhaps the first that can.

Also some stories from my childhood. Art as a live service. I’m wrong a lot so maybe I’m wrong about this stuff.

Music: “Un coin tranquille — Instrumental Version” by Nono feat. Anat Moshkovski.
I got it on Artlist (like most of the music on the channel) which is a royalty free library that I understand pays their artists pretty well.

AI is being used to generate everything from images to text to artificial proteins, and now another thing has been added to the list: speech. Last week researchers from Microsoft released a paper on a new AI called VALL-E that can accurately simulate anyone’s voice based on a sample just three seconds long. VALL-E isn’t the first speech simulator to be created, but it’s built in a different way than its predecessors—and could carry a greater risk for potential misuse.

Most existing text-to-speech models use waveforms (graphical representations of sound waves as they move through a medium over time) to create fake voices, tweaking characteristics like tone or pitch to approximate a given voice. VALL-E, though, takes a sample of someone’s voice and breaks it down into components called tokens, then uses those tokens to create new sounds based on the “rules” it already learned about this voice. If a voice is particularly deep, or a speaker pronounces their A’s in a nasal-y way, or they’re more monotone than average, these are all traits the AI would pick up on and be able to replicate.

The model is based on a technology called EnCodec by Meta, which was just released this part October. The tool uses a three-part system to compress audio to 10 times smaller than MP3s with no loss in quality; its creators meant for one of its uses to be improving the quality of voice and music on calls made over low-bandwidth connections.

Summary: Combining neuroimaging and EEG data, researchers recorded the neural activity of people while listening to a piece of music. Using machine learning technology, the data was translated to reconstruct and identify the specific piece of music the test subjects were listening to.

Source: University of Essex.

A new technique for monitoring brain waves can identify the music someone is listening to.