Novel AI-based software for better musical inspiration, creativity and composition
Building on the successful outcomes of the FP7-ICT initiative Lrn2Cre8, the EU-funded I2C8 project “brings parts of that research closer to market by exploiting results related to creativity and automatic music generation technologies,” says coordinator Dr Stefan Oertl. I2C8 developed a new software product for music chord generation with intelligent and automatic features. “Simplicity and ease of use are paramount. The software was designed with quick results in mind. Our aim is to inspire those who want to compose, not to deliver complete compositions.” Computer-supported creativity The application comes in the form of a plug-in for MIDI sequencers in digital audio workstations. The plug-in encourages and inspires composers to explore loops through pattern definition, position locking and generation into unlocked positions. Degrees of diatonicity of generated sequences can be examined and parameters for voicing the sequences manipulated. The I2C8 software is primarily aimed at semi-pro and pro music producers of loop-based, beat-driven, bass-heavy genres of electronic dance music who want to optimise their workflow during a creative process that differs somewhat from more traditional forms of music. Genre-typical, the first-generation I2C8 plug-in governs triad logic. Future versions of the software may incorporate more complex chord types. The software captures existing meaning in the form of a statistical model and combines it with constraints that can be defined by the composer. This is done to recommend potentially interesting chord sequences. However, the composer decides which chord sequence is used in a given musical context. The software utilises AI methods to provide full autonomy over creative processes. Unique intelligent software tool for music chord generation “We’re not aware of another application/plug-in that employs a user interface concept like I2C8,” says Dr Oertl. “We tried to make use of the plug-in as straightforward as possible.” For the structural representation of chord sequences, a simple graphical, idiosyncratic pattern language is used that enables results to be immediately viewed and listened to. This fosters an explorative and playful method when looking for and finding new and interesting chord progressions. “The method implemented by the plug-in clearly separates it from other tools that are already on the market,” adds Dr Oertl. “Most of these tools could be described as chord recommendation engines or chord sequence builders, whereas we generate a set of full chord sequences that satisfy a given structural pattern.” He explains that the unique selling point of the I2C8 approach is the use of a machine learning model as the foundation for chord generation. Also, user communication takes place through an idiosyncratic pattern language conveyed by the user interface and not through more or less explicit implementations of music theory. Project partners are currently exploring the software’s benefits for DJs and producers of electronic music during their live sets. It’s entering a public beta phase soon, and a market launch is planned for the third quarter of 2018. “The I2C8 software satisfies the need of composers and producers who want full control over their creative musical output and are not fond of robots showing them the way,” concludes Dr Oertl. “The human remains at the centre of the decision-making process.”
Keywords
I2C8, music, composer, chord sequence, producers, chord generation, MIDI sequencer
