Madrid, 10 ago. (European Press) –
Musicians can find inspiration and new creative directions to write songs with The technology developed by researchers at the University of Waterloo.
LyricJamIt is a real-time system that uses artificial intelligence (AI) to generate lines of live instrumental music lyrics, and was created by members of the university’s Natural Language Processing Laboratory.
The lab, led by Olga Vishtomova, a designated engineering professor in computer science, has been researching creative applications of artificial intelligence for several years.
Initial laboratory work led to the creation of a system Learn the artists’ musical expressions and generate lyrics in their style.
Recently, Vechtomova, along with Waterloo graduate students Gaurav Sahu and Dhruv Kumar, have developed a technique that relies on various aspects of music, such as chord progression, rhythm, and instrumentation to synthesize lyrics that reflect the expressed moods and emotions of live music.
When a musician or band plays instrumental music, the system constantly receives raw audio clips, which the neural network processes to generate new lines of song lyrics. Artists can use fonts to compose their own lyrics.
“The purpose of the system is not to write a song for the artist,” Vishtomova explains. “Instead, we want to help artists realize their own creativity. The system generates poetic lines with new metaphors and expressions, which may lead artists in creative directions they haven’t explored before.”
The neural network designed by the researchers identifies the themes, words, and stylistic devices associated with different aspects of the music captured in each audio clip.
For example, researchers note that the words created for background music are very different from those for cheerful music.
The research team conducted a study on users, Invite musicians to play instruments live while using the system.
“The unexpected discovery was that the participants were encouraged by the lines created for improvisation,” Vishtomova said. “For example, the lines have inspired artists to compose the strings a little differently and take their improvisation in a new direction than was originally intended. Some musicians have also used the lines to see if their improvisation has the desired emotional effect.”
Another finding from the study sheds light on the co-creative side of the experiment. Participants commented that they viewed the system as a non-critical intervention partner and were encouraged to play their musical instruments even if they were not actively trying to write lyrics.
Since the launch of LyricJam in June of this year, more than 1,500 users around the world have tried it.
The team’s research, scheduled to be presented at the International Conference on Computational Innovation in September, Previously posted on arXiv.
“Award-winning zombie scholar. Music practitioner. Food expert. Troublemaker.”