Robot With Glowing Baton

Three robotic arms stand on the podium, each with a glowing baton in their hand-like apparatuses. The creature has been tasked with conducting the world-renowned Dresden Symphony Orchestra in a concert this past weekend in Dresden. In total, 16 brass players and four percussionists from the Dresden Synfoniker followed the instructions of the robot.

The robot, a MAiRA Pro S nicknamed ‘Franka Emika’ has astonishing control over details. Each robotic arm has seven joints which allow it to conduct exactly as a human arm would. Humans also helped the robot perfect its movements. The movements were stored separately for each robot. Each one learned to keep the beat and indicate changes in dynamics.

More information:

https://www.dw.com/en/dresden-symphony-orchestra-puts-robotic-conductor-in-charge/a-70490890

Dream Track

YouTube is launching a new tool powered by artificial intelligence that will allow users to record audio using the voices of some of today’s most famous musicians, the company announced Thursday. The new product, called Dream Track, is a collaboration with nine musical artists. Through text-based directions, users can auto-generate short tracks of up to 30 seconds in the voice and style of a participating artist.

The launch looks to capitalize on the intersection of AI technology and music, and as it reckons with the new technology’s ethical and legal implications alongside artists and major record labels. In the past, the practice of using artists’ voices without their consent for generative AI, likened to plagiarism, has come under fire by labels and lawmakers, alike.

More information:

https://www.cnbc.com/2023/11/16/youtube-debuts-ai-tool-dream-track-that-mimics-vocals-of-artists.html

Re-creating Pink Floyd Song from Listeners’ Brain Activity

Scientists have demonstrated that the brain’s electrical activity can be decoded and used to reconstruct music. A new study analyzed data from 29 people who were already being monitored for epileptic seizures using postage-stamp-size arrays of electrodes that were placed directly on the surface of their brain.

As the participants listened to Pink Floyd’s 1979 song “Another Brick in the Wall, Part 1,” the electrodes captured the electrical activity of several brain regions attuned to musical elements such as tone, rhythm, harmony and lyrics. Employing machine learning, the researchers reconstructed garbled but distinctive audio of what the participants were hearing.

More information:

https://www.scientificamerican.com/article/neuroscientists-re-create-pink-floyd-song-from-listeners-brain-activity/

Brainwaves Identify Music Being Listened To

Researchers at the University of Essex hope the project could lead to helping people with severe communication disabilities such as locked-in syndrome or stroke sufferers by decoding language signals within their brains through non-invasive techniques. Essex scientists wanted to find a less invasive way of decoding acoustic information from signals in the brain to identify and reconstruct a piece of music someone was listening to. Whilst there have been successful previous studies monitoring and reconstructing acoustic information from brain waves, many have used more invasive methods such as electrocortiography (ECoG) - which involves placing electrodes inside the skull to monitor the actual surface of the brain.

Researchers used a combination of two non-invasive methods - fMRI, which measures blood flow through the entire brain, and electroencephalogram (EEG), which measures what is happening in the brain in real time - to monitor a person’s brain activity whilst listening to a piece of music. Using a deep learning neural network model, the data was translated to reconstruct and identify the piece of music. Music is a complex acoustic signal, sharing many similarities with natural language, so the model could potentially be adapted to translate speech. The eventual goal of this strand of research would be to translate thought, which could offer an important aid in the future for people who struggle to communicate, such as those with locked-in syndrome.

More information:

https://www.essex.ac.uk/news/2023/01/19/decoding-brainwaves-to-identify-music-listened-to