The goal is to create a tool that allows artists to explore themes and ideas related to the emotions produced by their music.

Unlike other lyric-generation systems, LyricJam can suggest words to match the rhythm, chords or instruments in real-time as an artist plays live music. This can help artists find new words that fit their music.

The researchers have been developing LyricJam for several years. Initially, the goal was to generate lyrics according to an artist’s style by analysing their existing words and music. Now the system is heading towards a model where artificial intelligence acts as a “musical partner” that suggests new possibilities to creators and inspires them with new creations.

“The goal was to design a system that can generate lyrics reflecting the mood and emotions expressed through various aspects of music, such as chords, instruments and tempo,” said Olga Vechtomova, one of the researchers on the project.

“We set out to create a tool that musicians could use to get inspiration for their own songwriting.”

In essence, the system processes live music and generates lyrics, which artists can then review to be inspired by them or to adapt them. This gives them an opportunity to discover new themes or ideas they might not have previously considered.

The software converts audio files into spectrograms – visual representations of audio – and uses its learning models to generate lyrics accordingly.

The researchers believe LyricJam could become an extremely valuable tool for artists looking for unique lyrics and wishing to diversify their themes. They are continuing to refine the system and design other tools to improve its capabilities.