Science.-A tool that inspires lyrics for instrumental music

MADRID, 10 (EUROPA PRESS)

Musicians can find inspiration and creative new directions for songwriting with technology developed by researchers at the University of Waterloo.

LyricJam, a real-time system that uses artificial intelligence (AI) to generate lines of lyrics for live instrumental music, has been created by members of the University’s Natural Language Processing Laboratory.

The lab, led by Olga Vechtomova, a cross-appointed Computer Science Professor of Engineering, has been researching creative applications of AI for several years.

The initial work of the laboratory led to the creation of a system that learns the musical expressions of the artists and generates lyrics in their style.

Recently, Vechtomova, together with Waterloo graduate students Gaurav Sahu and Dhruv Kumar, developed technology that draws on various aspects of music, such as chord progressions, tempo, and instrumentation to synthesize lyrics that reflect the mood and emotions expressed. for live music.

When a musician or band plays instrumental music, the system continuously receives raw audio clips, which the neural network processes to generate new lines of lyrics. Artists can use the lines to compose their own song lyrics.

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

The neural network designed by the researchers learns which themes, words, and stylistic devices are associated with different aspects of the music captured in each audio clip.

For example, the researchers observed that the lyrics generated for background music are very different from those for upbeat music.

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

“An unexpected finding was that the participants were encouraged by the lines generated to improvise,” Vechtomova said. “For example, the lines inspired artists to structure the chords a little differently and take their improvisation in a new direction than it was originally intended. Some musicians also used the lines to check whether their improvisation had the desired emotional effect. “.

Another finding from the study highlighted the co-creative aspect of the experience. Participants commented that they viewed the system as an uncritical interference partner and were encouraged to play their musical instruments even if they weren’t actively trying to write lyrics.

Since LyricJam was launched in June of this year, more than 1,500 users around the world have tried it.

The team’s research, which will be presented at the International Conference on Computing Creativity in September, has been pre-published on arXiv.

Those interested in trying LyricJam can access it at https://lyricjam.ai.