This episode contains: All three hosts are here, slowly rotating around the sun, to bring you science and science fiction. Devon explains why he can’t record this afternoon (the answer is football). Ben tells us about the ongoing woes of being a home owner. Steven and Ben talk about playing Walkabout Mini Golf on VR.
Listen To This: MusicLM: Generating Music From Text. MusicLM is a model generating high-fidelity music from text descriptions such as “a calming violin melody backed by a distorted guitar riff”. MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes.
https://google-research.github.io/seanet/musiclm/examples/
Riffusion’s AI generates music from text using visual sonograms. Riffusion is an AI model that generates music from text prompts by creating a visual representation of sound and converting it to audio for playback. It uses a fine-tuned version of the Stable Diffusion 1.5 image synthesis model, applying visual latent diffusion to sound processing in a novel way.
Big Question: What sci-fi universe would you want to live in? What if you had to support your current family and could not count on being a hero in that story? What if Skype kept disconnecting you?
The Official Science Faction Podcast Webpage 