Input-Envelope-Output: Auditable Generative Music Rewards in Sensory-Sensitive Contexts

TL;DR

This paper introduces a new auditable generative music system architecture that explicitly enforces safety bounds, making it suitable for sensory-sensitive contexts like autism spectrum disorder and enabling verifiable safety guarantees.

Contribution

The paper proposes the Input-Envelope-Output (I-E-O) framework, a novel architecture for safe, auditable generative music systems, and demonstrates its implementation in MusiBubbles.

Findings

The I-E-O architecture effectively enforces safety constraints.

MusiBubbles demonstrates practical application in sensory-sensitive environments.

The framework supports auditability and reproducibility in generative music systems.

Abstract

Generative feedback in sensory-sensitive contexts poses a core design challenge: large individual differences in sensory tolerance make it difficult to sustain engagement without compromising safety. This tension is exemplified in autism spectrum disorder (ASD), where auditory sensitivities are common yet highly heterogeneous. Existing interactive music systems typically encode safety implicitly within direct input-output (I-O) mappings, which can preserve novelty but make system behavior hard to predict or audit. We instead propose a constraint-first Input-Envelope-Output (I-E-O) framework that makes safety explicit and verifiable while preserving action-output causality. I-E-O introduces a low-risk envelope layer between user input and audio output to specify safe bounds, enforce them deterministically, and log interventions for audit. From this architecture, we derive four verifiable design principles and instantiate them in MusiBubbles, a web-based prototype. Contributions include the I-E-O architecture, MusiBubbles as an exemplar implementation, and a reproducibility package to support adoption in ASD and other sensory-sensitive domains.