AudioLM, developed by Google researchers, generates audiothat fits the style of prompt, including complex sounds like piano music, orpeople speaking, in a way that is almost indistinguishable from the original recording.The technique shows promise for speeding up the process of training AI togenerate audio, and it could eventually be used to auto-generate music toaccompany vidoes.
Read more here.
MIT Technology Review
The MIT community is driven by a shared purpose: to make a better world through education, research, and innovation. We are fun and quirky, elite but not elitist, inventive and artistic, obsessed with numbers, and welcoming to talented people regardless of where they come from.
