Archive for the ‘media & arts’ category: Page 4

Feb 27, 2023

The Neurophysiology of Enchantment: How Music Casts Its Spell on Us

Posted by in category: media & arts

Music so readily transports us from the present to the past, or from what is actual to what is possible.

Feb 23, 2023

Spotify’s AI-powered DJ will suggest songs and provide insights

Posted by in categories: media & arts, robotics/AI

In addition to queueing up songs, it will provide insightful commentary too.

Music streaming service Spotify is the latest tech company to launch an artificial intelligence (AI)-powered product. Dubbed DJ, the service was launched for users in the U.S. and Canada on Wednesday, a company press release said.

Continue reading “Spotify’s AI-powered DJ will suggest songs and provide insights” »

Feb 18, 2023

A New AI Research from Italy Introduces a Diffusion-Based Generative Model Capable of Both Music Synthesis and Source Separation

Posted by in categories: media & arts, robotics/AI

Human beings are capable of processing several sound sources at once, both in terms of musical composition or synthesis and analysis, i.e., source separation. In other words, human brains can separate individual sound sources from a mixture and vice versa, i.e., synthesize several sound sources to form a coherent combination. When it comes to mathematically expressing this knowledge, researchers use the joint probability density of sources. For instance, musical mixtures have a context such that the joint probability density of sources does not factorize into the product of individual sources.

A deep learning model that can synthesize many sources into a coherent mixture and separate the individual sources from a mixture does not exist currently. When it comes to musical composition or generation tasks, models directly learn the distribution over the mixtures, offering accurate modeling of the mixture but losing all knowledge of the individual sources. Models for source separation, in contrast, learn a single model for each source distribution and condition on the mixture at inference time. Thus, all the crucial details regarding the interdependence of the sources are lost. It is difficult to generate mixtures in either scenario.

Taking a step towards building a deep learning model that is capable of performing both source separation and music generation, researchers from the GLADIA Research Lab, University of Rome, have developed Multi-Source Diffusion Model (MSDM). The model is trained using the joint probability density of sources sharing a context, referred to as the prior distribution. The generation task is carried out by sampling using the prior, whereas the separation task is carried out by conditioning the prior distribution on the mixture and then sampling from the resulting posterior distribution. This approach is a significant first step towards universal audio models because it is a first-of-its-kind model that is capable of performing both generation and separation tasks.

Continue reading “A New AI Research from Italy Introduces a Diffusion-Based Generative Model Capable of Both Music Synthesis and Source Separation” »

Feb 17, 2023

Let Food Be Thy Medicine

Posted by in categories: biotech/medical, business, economics, education, food, health, media & arts, policy

In collaboration with the UC San Diego Center for Integrative Nutrition, the Berry Good Food Foundation convenes a panel of experts to discuss the rise of comprehensive medicine and nutritional healing to treat chronic disease and maintain general well-being. [6/2018] [Show ID: 33486]

Future Thought Leaders.

Continue reading “Let Food Be Thy Medicine” »

Feb 16, 2023

Super Soldiers

Posted by in categories: futurism, media & arts

Go to for 15% off your order! Brought to you by Raycon.
We often see stories of invincible warriors with superhuman abilities combating monstrous threats, but are the days of super soldiers nearly upon us, and could they be the biggest threat of all?

Visit our Website:
Join Nebula:
Support us on Patreon:
Support us on Subscribestar:
Facebook Group:
Twitter: on Twitter and RT our future content.
SFIA Discord Server:

Continue reading “Super Soldiers” »

Feb 16, 2023

The math behind engineering living things (TMEB #3)

Posted by in categories: bioengineering, mathematics, media & arts

The math behind Evo-devo~

Continue reading “The math behind engineering living things (TMEB #3)” »

Feb 16, 2023

Google AI generates musical backing tracks to accompany singers

Posted by in categories: information science, media & arts, robotics/AI

Google has trained an artificial intelligence, named SingSong, that can generate a musical backing track to accompany people’s recorded singing.

To develop it, Jesse Engel and his colleagues at Google Research used an algorithm to separate the instrumental and vocal parts from 46,000 hours of music and then fine-tuned an existing AI model – also created by Google Research, but for generating speech and piano music – on those pairs of recordings.

Feb 16, 2023

Black Sabbath- Electric Funeral (Music Video)

Posted by in categories: entertainment, media & arts, military

A video about nuclear weapons. The song is “Electric Funeral” by the British heavy metal band Black Sabbath off their 1970 album Paranoid, an extremely influential album for metal and rock music.

Feb 13, 2023

AI-powered robotic arm collaborates with artists to create art

Posted by in categories: media & arts, robotics/AI

FRIDA can create finger paintings based on human inputs, photographs, and music.

“AI is the future!” is a statement of the past now, as AI is no longer the future but our present. After ChatGPT shocked the whole world with its abilities, researchers at Carnegie Mellon University created an AI-powered robot that could create exceptional artwork on physical canvas with the help of simple text prompts, according to a press release.

Continue reading “AI-powered robotic arm collaborates with artists to create art” »

Feb 12, 2023

From the Shadows: A New Method for X-Ray Color Imaging

Posted by in categories: biotech/medical, chemistry, computing, media & arts

Researchers at the University of Göttingen have created a new approach to generate colored X-ray images. Previously, the only way to determine the chemical composition and arrangement of components in a sample using X-ray fluorescence analysis was to focus X-rays on the entire sample and scan it, which was both time-consuming and costly. The new method allows for the creation of an image of a large area with just one exposure, eliminating the need for focusing and scanning. The findings were published in the journal Optica.

In contrast to visible light, there are no comparably powerful lenses for “invisible” radiation, such as X-ray, neutron, or gamma radiation. However, these types of radiation are essential, for example, in nuclear medicine and radiology, as well as in industrial testing and material analysis.

Uses for X-ray fluorescence include analyzing the composition of chemicals in paintings and cultural artifacts to determine authenticity, origin, or production technique, or the analysis of soil samples or plants in environmental protection. The quality and purity of semiconductor components and computer chips can also be checked using X-ray fluorescence analysis.

Page 4 of 8212345678Last