Chih-Heng Chang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chih-Heng Chang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chih-Yu Tsai
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication - Jian-Jiun Ding
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication - Keng-Seng Ho
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication - Kuan-Lin Chen
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication - Yu-Siang Huang
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 321-330
AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
Controllable music editing is to modify high-level attributes while strictly preserving rhythmic and melodic structures. However, this task is challenged by a semantic-structural entanglement: steering methods often degrade structure to achieve editing performance, while structural adaptors suppress semantic responsiveness. We propose AnchorSteer, a framework that disentangles this tension by coupling structural anchoring with self-discovered semantic steering. The proposed approach probes internal representations to extract interpretable, label-free concept vectors via a self-supervised reconstruction objective, isolating attributes without curated data. During editing, these portable, plug-and-play concept vectors are injected into diffusion hidden manifolds while a structural adaptor enforces consistency. Variants for unconditioned and conditioned injections are provided to balance robustness and semantic strength. Experiments on ZoME-Bench and subjective tests show that the proposed framework outperforms both steering-only and anchoring-only baselines, enabling significant semantic transformations with high-fidelity structural preservation.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 321-330
Open AccessAnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
Controllable music editing is to modify high-level attributes while strictly preserving rhythmic and melodic structures. However, this task is challenged by a semantic-structural entanglement: steering methods often degrade structure to achieve editing performance, while structural adaptors suppress semantic responsiveness. We propose AnchorSteer, a framework that disentangles this tension by coupling structural anchoring with self-discovered semantic steering. The proposed approach probes internal representations to extract interpretable, label-free concept vectors via a self-supervised reconstruction objective, isolating attributes without curated data. During editing, these portable, plug-and-play concept vectors are injected into diffusion hidden manifolds while a structural adaptor enforces consistency. Variants for unconditioned and conditioned injections are provided to balance robustness and semantic strength. Experiments on ZoME-Bench and subjective tests show that the proposed framework outperforms both steering-only and anchoring-only baselines, enabling significant semantic transformations with high-fidelity structural preservation.