This paper describes ongoing work in programming a live performance system for interpreting melodies in ways that mimic Irish traditional dance music practice and that allows plug-and-play human interaction. Existing performance systems are almost exclusively aimed at piano performance and classical music and few are aimed specifically at traditional music. We develop a rule-based approach using expert knowledge that converts a melody into control parameters to synthesize an expressive MIDI performance, focusing on ornamentation, dynamics and subtle time deviation. Furthermore, we make the system controllable (e.g., via knobs or expression pedals) such that it can be controlled in real time by a musician. Our preliminary evaluations show the system can render expressive performances mimicking traditional practice and allows for engaging with Irish traditional dance music in new ways. We provide several examples online (See this website: https://www.kth.se/profile/bobs/page/research-data).

A text-to-music (TTM) model should synthesize audio that reflects the concepts in a given prompt as long as it has been trained on those concepts. If a prompt references concepts that the TTM model has not been trained on then the audio it synthesizes will likely not match. This paper investigates the application of a simple gradient-based approach called textual inversion (TI) to expand the concept vocabulary of a trained TTM model without compromising the fidelity of concepts on which it has already been trained. We apply this technique to MusicGen and measure its reconstruction and editability quality, as well as its subjective quality. We see TI can expand the concept vocabulary of a pretrained TTM model, thus making it personalized and more controllable without having to finetune the entire model.

We chart the creative journeys of two groups of musicians as they explored how to engage with an AI system developed for the live performance of Irish Traditional Dance Music. A group of expert Irish musicians participated in an extended workshop to refine the system while a professional contemporary folk duo composed and rehearsed material for a public show. Drawing on the standard definition of creativity, we chart their creative journeys across a landscape we define by the two dimensions of originality and effectiveness. We reveal the importance of authenticity to a traditional practice as an opposing force to creativity and consider how the tension between these shaped their musical journeys. We generalise five strategies that move creative practitioners across this landscape in different directions: proving your chops, finding your place, perfecting the nuances, innovating, and glitching.

Modeling harmonic progressions in symbolic music is a complex task that requires generating musically coherent and varied chord sequences. In this study, we employ a transformer-based architecture trained on a comprehensive dataset of 48,072 songs, which includes an augmented set of 4,300 original pieces from the iReal Pro application transposed across all chromatic keys. We introduce a novel tokenization and voicing encoding strategy designed to enhance the musicality of the generated chord progressions. Our approach not only generates chord progression suggestions but also provides corresponding voicings tailored for instruments such as piano and guitar. To evaluate the effectiveness of our model, we conducted a listening test comparing the harmonic progressions produced by our approach against those from a baseline model. The results indicate that our model generates progressions with more fluid voicings, coherent harmonic motion, and plausible chord suggestions, effectively utilizing repetition and variation to enhance musicality.

Online commercial artificial intelligence (AI) platforms for generating music from text prompts (AI music) are now being used by many users to create millions of music audio recordings daily. Some AI music is appearing in advertising, music playlists of restaurants and gyms, and even hit music charts, in many countries. How are users engaging with these text‑to‑music AI platforms, where text is a principal mode of interaction to specify prompts (e.g., free terms), lyrics (e.g., sung terms), and tags (e.g., high‑level stylistic terms)? What languages appear? What characterizes prompts, lyrics, and tags? How are mentions of real artists used? What kind of additional instructions (metatags) are used? To address these questions, we assemble and analyze a collection of 101, 953 songs generated from May to October 2024 by 60, 342 users of Suno and Udio. Using a combination of state‑of‑the‑art text‑embedding models, dimensionality reduction, and clustering methods, we analyze the prompts, tags, and lyrics and automatically annotate and display the processed data in interactive plots. Our results reveal prominent themes in lyrics, language preferences, and prompting strategies, as well as peculiar attempts at steering models through the use of metatags. We share our code and data resources to promote further musicological study of AI music.

Some discourses about music and AI are frustratingly shallow and insular, raising outdated musical tropes and ignoring modern developments, flattening the rich and varied functions of music in life, and overlooking serious ethical issues with the technology (creating it, maintaining it, using it, and imposing it). We respond to this shallowness via artistic activism and agonistic artistic research, resulting in the site-specific work “oljud—bruit(n)”. Our action was directed at an “AI music composition” competition in2025 organised as part of a very expensive engineering workshop focused on music generation research, but our motivations are more broad. This paper records the context, composition and realization of our “sonic manifesto of resistance”, which was ultimately disqualified from the competition.

We present a novel computer application for real-time exploration of microtonal harmonies through intuitive visualization and integrated MIDI controllers, bridging theoretical concepts and practical musical applications. We extend modern harmonic principles from 12-tone equal temperament (12-TET), incorporating interval distinctions from 31-TET (subminor, neutral, supermajor), and further expanding into detailed harmonic possibilities of 53-tone equal temperament (53-TET). Our application leverages modal interchange and parallel chord substitutions, offering intuitive navigation through microtonal harmonic trajectories. The implementation utilizes MIDI Polyphonic Expression (MPE) via our custom MaxForLive application, The Bridge, ensuring precise microtonal control and compatibility with digital audio workstations (Ableton Live 11/12). The system includes real-time visualization, interactive chord manipulation, and a comprehensive Scale Editor for harmonic experimentation. Through practical examples and theoretical analysis, we demonstrate how this approach reveals new harmonic possibilities while maintaining connections to established modal frameworks. This research contributes to the growing microtonal music field by providing theoretical foundations and practical tools that incorporate extended tuning systems into contemporary musical practice.

Knowing which sounds can be produced by a simulated vocal model and how they are connected to its articulatory behavior is not trivial. Being able to map this out can be interesting for applications that make use of the extended capabilities of a voice, e.g., singing or vocal imitations. We present a method that achieves this for a state-of-the-art articulatory vocal model (VocalTractLab) by combining it with a recent Quality-Diversity algorithm (CMA-MAE) and audio embeddings obtained through a multi-modal pretrained model (CLAP). The text-capabilities of CLAP make it possible to steer the exploration through a text prompt. We show that the method explores more efficiently than a random sampling baseline, covering more of the measure space and achieving higher objective scores. We provide several listening examples and the source code for a scalable implementation.