LyricJam, a real-time system that uses artificial intelligence (Al) to produce lyrics (歌词) for live instrumental music, was created by members of the University’s Natural Language Processing Lab.

The lab, led by Olga Vechtomova, a Waterloo Engineering professor in Computer Science, worked on the creation of a system that learns musical expressions of artists and generates lyrics in their style. Meanwhile, the lyrics could reflect the moods and emotions expressed by live music.

As a musician or a band plays instrumental music, the system continuously receives the raw audio clips (音频片段), which the neural (神经的) network processes to generate new lyric lines. The artists can then use the lines to create their own song lyrics. The neural network designed by the researchers learns what lyrical themes, words and stylistic devices are associated with different aspects of music in each audio clip.

“The purpose of the system is not to write a song for the artist,” Vechtomova explains. “Instead, we want to help artists realize their own creativity. The system produces poetic lines with new metaphors and expressions, potentially leading the artists in creative directions that they haven’t explored before.”

The research team conducted a user study, inviting musicians to play live instruments while using the system.

“One unexpected finding was that participants felt encouraged by the produced lyrics to improvise (即兴创作), ” Vechtomova said. “For example, the lyrics inspired artists to take their improvisation in a new direction. Some musicians also used the lyrics to check if their improvisation had the desired emotional effect.”

Participants commented that they viewed the system as a partner and felt inspired to play their musical instruments even if they were not actively trying to write lyrics. Since LyricJam went live, plenty of users worldwide have tried it out.

“At almost any given age，most of us are getting better at some things and worse at others，”Joshua Hartshorne，an MIT cognitive(认知的)science researcher and the lead author of a study looking at how intelligence changes as we age，told Business Insider.His team quizzed thousands of people aged 10—90 on their ability to do things like remembering lists of words，recognizing faces，learning names，and doing math.Their results suggest that no matter your age，there’s almost always a new peak on the horizon.

The human brain has a remarkable capacity to recognize and identify faces，and scientists are just beginning to learn why.On average，we know that our ability to learn and remember new faces appears to peak shortly after our 30th birthday.

Having trouble focusing? The study suggests that our ability to maintain attention improves with age，reaching its peak around age 43.While younger adults may excel in the speed and flexibility of information processing，adults approaching their mid-years may have the greatest capacity to remain focused.

Dating is tough.One of the reasons could be that we’re generally bad at reading other people’s emotions until we reach our late 40s.That’s according to one component of Hartshorne’s study，which involved showing thousands of people images of faces cropped tightly around the eye area.Participants were asked to describe the emotion the person in the photo was feeling.Performance peaked for people aged around 48.

Many people believe that their math skills decline after they leave school and stop practicing arithmetic.But the next time you try to split up a check，keep this in mind:your ability to do basic subtraction and division doesn’t reach its apex until your 50th birthday.

Ever wonder why you always lose at Scrabble? Good news:Your best days may be ahead.According to people’s scores on multiple—choice vocabulary tests，most of us don’t reach our peak wordsmithing abilities until we’re in our late 60s or early 70s.