Papers

This paper introduces the Neuralacoustics framework for researching Deep Learning architectures towards real-time acoustics simulations and benchmarking for musical applications.

A reinforcement learning agent for live sound improvisation

This paper details a collaboration with Arca to advance generative MIDI models, resulting in a seven-hour MRP installation showcasing expressive, uncanny MIDI continuations created using Notochord.

Designing the interaction and guiding further development through user feedback for a generative AI step sequencer

A Diverse Instrument Symphonic Ensemble performs with AI technologies

Improvisation with guitar and live electronics based on granular synthesis, machine listening and feedback

This paper introduces a Transformer-based melody harmonization method aimed at generating chord progressions with varying levels of rhythmic complexity.

This paper discusses a new cross-disciplinary project building an AI model for popular song generation in the mixcode language Hinglish.

AIMC2024 Performance Proposal

Generative music performance video of jazz trio and robotic instruments

Providing automatically generated guitar chord tablature practice material given chord name input

The use of AI and traditional Chinese instruments in sonic art.

Learning to work with audio neural synthesis in the Music Conservatoire through the lens of RSE-facilitated artistic processes

Addressing Legal and Ethical Requirements and Associated Challenges of Managing Multimodal Music Datasets used in AI Systems

Off-the-shelf is a mixed reality duet musical improvisation that redefines co-creative artificial musical experiences through a minimal aesthetic dialogue.

We present a small-scale framework for generating phrase-level symbolic music with limited training data. The human evaluation shows that our framework outperforms the state-of-the-art transformer-based models in terms of overall quality and rhythmic regularity.

A sentiment analysis towards AI-generated music through the utilization of Latent Dirichlet Allocation (LDA) methodology to investigate 5,059 YouTube comments found in 212 videos of an AI music channel.

This paper delves into SpeechBrain, OpenAI and CoquiTTS voice and speech models within a research-through-design inspired, exploratory research engagement with pre-trained speech synthesis models to find their musical affordances in an experimental vocal practice.

A qualitative exploration of the music knowledge of LLMs and their use for music creation

🦜➡️🏴‍☠️

This study examines the AI negativity bias in the context of VR concert experience.

An argument for the role of the artist in the future of Generative A.I. produced artworks

Conceptual and experimental research on the issue of (dis)embodiment in software for human-machine co-improvisation based on machine learning.

Live electronic+vocal performance