NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912898534604800 |
|---|---|
| author | Wen, Yufan Liu, Zhaocheng Hua, YeGuo Guo, Ziyi Zhang, Lihua Yuan, Chun Wu, Jian |
| author_facet | Wen, Yufan Liu, Zhaocheng Hua, YeGuo Guo, Ziyi Zhang, Lihua Yuan, Chun Wu, Jian |
| contents | Synthesizing coherent soundtracks for long-form videos remains a formidable challenge, currently stalled by three critical impediments: computational scalability, temporal coherence, and, most critically, a pervasive semantic blindness to evolving narrative logic. To bridge these gaps, we propose NarraScore, a hierarchical framework predicated on the core insight that emotion serves as a high-density compression of narrative logic. Uniquely, we repurpose frozen Vision-Language Models (VLMs) as continuous affective sensors, distilling high-dimensional visual streams into dense, narrative-aware Valence-Arousal trajectories. Mechanistically, NarraScore employs a Dual-Branch Injection strategy to reconcile global structure with local dynamism: a \textit{Global Semantic Anchor} ensures stylistic stability, while a surgical \textit{Token-Level Affective Adapter} modulates local tension via direct element-wise residual injection. This minimalist design bypasses the bottlenecks of dense attention and architectural cloning, effectively mitigating the overfitting risks associated with data scarcity. Experiments demonstrate that NarraScore achieves state-of-the-art consistency and narrative alignment with negligible computational overhead, establishing a fully autonomous paradigm for long-video soundtrack generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09070 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control Wen, Yufan Liu, Zhaocheng Hua, YeGuo Guo, Ziyi Zhang, Lihua Yuan, Chun Wu, Jian Sound Artificial Intelligence Audio and Speech Processing Synthesizing coherent soundtracks for long-form videos remains a formidable challenge, currently stalled by three critical impediments: computational scalability, temporal coherence, and, most critically, a pervasive semantic blindness to evolving narrative logic. To bridge these gaps, we propose NarraScore, a hierarchical framework predicated on the core insight that emotion serves as a high-density compression of narrative logic. Uniquely, we repurpose frozen Vision-Language Models (VLMs) as continuous affective sensors, distilling high-dimensional visual streams into dense, narrative-aware Valence-Arousal trajectories. Mechanistically, NarraScore employs a Dual-Branch Injection strategy to reconcile global structure with local dynamism: a \textit{Global Semantic Anchor} ensures stylistic stability, while a surgical \textit{Token-Level Affective Adapter} modulates local tension via direct element-wise residual injection. This minimalist design bypasses the bottlenecks of dense attention and architectural cloning, effectively mitigating the overfitting risks associated with data scarcity. Experiments demonstrate that NarraScore achieves state-of-the-art consistency and narrative alignment with negligible computational overhead, establishing a fully autonomous paradigm for long-video soundtrack generation. |
| title | NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.09070 |