Dramarrator: Object-Based Audio Editing for Audio Drama Production from Books

2026-08-08

AI Summary

This work proposes an object-based audio editing approach for audiobook adaptation, introducing an object-oriented paradigm to narrative audio production. Addressing the cumbersome, labor-intensive process traditionally required to coordinate speech, sound effects, and music—particularly when local script revisions necessitate extensive manual re-synchronization—the method leverages natural language processing to extract story objects from text and automatically associate them with corresponding audio assets. This enables multitrack composition and synchronized, cross-asset updates. User studies demonstrate that the approach significantly reduces cognitive workload and lowers the barrier to entry for creators, while fine-tuned outputs achieve near-professional quality. Furthermore, the framework exhibits strong potential for generalization to other forms of narrative audio due to its modularity, usability, and scalability.

Abstract

Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains labor-intensive, requiring them to interpret source material, author scripts, generate audio assets, and assemble them on a timeline. Because story elements like characters and scenes manifest across many interdependent assets, a single change can ripple into manual updates across the entire project. We present Dramarrator, an audio drama authoring tool built around object-based audio editing, where these story elements are represented as editable objects. Dramarrator extracts these objects from a book, generates linked audio assets (speech, sound effects, and music), and composes a multi-track audio drama. Edits to any object (e.g., a character's voice) automatically propagate to all dependent assets. In a user study with professionals (N=8), Dramarrator significantly lowered task load when creating audio dramas. A listener study (N=300) shows that creator-refined output from Dramarrator approaches the quality of productions made with existing professional tools, and an exploratory study (N=3) suggests object-based editing lowers entry barriers and generalizes beyond audio dramas.

Problem

• audio drama
• book adaptation
• object-based audio editing
• audio authoring
• manual editing

Innovation

• object-based audio editing
• audio drama generation
• automated asset linking
• interactive storytelling
• book-to-audio adaptation