Toggle light / dark theme

Meta has released AudioCraft, a new open-source generative AI framework that can produce music from simple text prompts. AudioCraft is based on a dynamic framework that enables high-quality, realistic audio and music generation from text-based user inputs. It aims to revolutionize music generation by empowering professional musicians to explore new compositions, indie game developers to enhance their virtual worlds with sound effects, and small business owners to add soundtracks to their Instagram posts, all with ease.

AudioCraft is based on a dynamic framework that enables high-quality, realistic audio and music generation from text-based user inputs. It aims to revolutionize music generation by empowering professional musicians to explore new compositions, indie game developers to enhance their virtual worlds with sound effects, and small business owners to add soundtracks to their Instagram posts, all with ease.

AudioCraft is a collection of three robust models: MusicGen, AudioGen and EnCodec. While MusicGen uses text-based user inputs to generate music, AudioGen performs a similar role for ambient sounds. Both are trained with Meta-owned and specifically licensed music and public sound effects, respectively. A recent release from the company offers an improved version of EnCodec. This decoder allows for high-quality music generation with fewer artifacts, based on the pre-trained AudioGen and all AudioCraft model weights and code.

Sometimes, the best place to hide a secret is in broad daylight. Just ask the sun.

“The sun is more surprising than we knew,” said Mehr Un Nisa, a postdoctoral research associate at Michigan State University. “We thought we had this star figured out, but that’s not the case.”

Nisa, who will soon be joining MSU’s faculty, is the corresponding author of a new paper in the journal Physical Review Letters that details the discovery of the highest-energy light ever observed from the sun.

The skin is the largest organ of the body, comprising several compartments and about 20 different cell types that are involved in various skin functions – complexity that is more than skin deep! [1] Skin aging is a multifactorial process that is impacted by several intrinsic and extrinsic factors. Constant exposure of the human skin to such stimuli impacts its function and accelerates aging resulting in dry skin, wrinkling, thinning of the epidermis, and reduced barrier integrity. While we notice most of those changes by looking in a mirror – something the cosmetics industry has leveraged to multi-billion dollar effect – older skin is more at risk of injury, less able to sense touch, heat and cold, slower to heal and more prone to cellulitis and other skin infections.

Aging is a complex and gradual process characterized by a reduction in function and reproducibility along with an increase in the incidence of degenerative diseases. Skin aging has been reported to be associated with the presence and accumulation of senescent cells. “A number of diseases that increase in older people may have a unifying underlying mechanism having to do with senescence,” says Ruth Montgomery, PhD, professor of medicine and epidemiology (microbial diseases) at Yale School of Medicine [2].

Senescent cells are those that have lost their proliferative capacity, are resistant to apoptosis, and secrete factors that can cause tissue deterioration and inflammation [3]. These factors are termed senescence-associated secretory phenotype (SASP) and can lead to extracellular matrix (ECM) deposition, impact epidermal stem cell renewal and worsen melanin synthesis.

Scientists at Purdue University are propelling the future of robotics and autonomous systems forward with their patent-pending method that improves typical machine vision and perception.

Zubin Jacob, the Elmore Associate Professor of Electrical and Computer Engineering in the Elmore Family School of Electrical and Computer Engineering, and research scientist Fanglin Bao have developed HADAR, or heat-assisted detection and ranging. Their research was featured on the cover of the July 26 issue of the peer-reviewed journal Nature.

Jacob said it is expected that one in 10 vehicles will be automated and that there will be 20 million robot helpers that serve people by 2030.