It is concluded that exposing the data provenance and generative processes of AI systems can help transform them from opaque tools into intelligible musical partners and that transparency is an important design factor for creative agency in intelligent instruments.
The hypothesis is that control and agency is distributed by machine learning’s algorithms, in which designer and performer, have to navigate through the feedback system made of gestures, latent space and spatialized sound.
Pablo Mollenhauer, Alejandra Pérez Núñez· 0 citations
It is argued that musical significance in ML-based instruments can emerge through duration, care, and collective intervention rather than virtuosic immediacy, arguing that musical significance in ML-based instruments can emerge through duration, care, and collective intervention rather than virtuosic immediacy.
This paper examines how multimodal mapping can function as a collaborative methodology in real-time audiovisual performance. It explores how functional codependency and real-time risk create bonds between artists, becoming fundamental narrative and dramaturgical vectors, and revealing the aesthetic influence of the t...
Roberto Alonso Trillo, Peter A. C. Nelson, Kratika Jain· Organised Sound· 0 citations
We present ScorePrompts, an interactive system in which users upload a score, receive natural-language descriptions of its musical structure, ask questions about specific passages, and inspect the corresponding analysis results in staff notation. Specialist MIR components first estimate harmony, tonality, cadences, for...
Emmanouil Karystinaios, Gerhard Widmer· 0 citations
