Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.03844 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913492701806592 |
|---|---|
| author | Liu, Haoxuan Wang, Zihao Hong, Haorong Feng, Youwei Yu, Jiaxin Diao, Han Xu, Yunfei Zhang, Kejun |
| author_facet | Liu, Haoxuan Wang, Zihao Hong, Haorong Feng, Youwei Yu, Jiaxin Diao, Han Xu, Yunfei Zhang, Kejun |
| contents | This paper introduces MetaBGM, a groundbreaking framework for generating background music that adapts to dynamic scenes and real-time user interactions. We define multi-scene as variations in environmental contexts, such as transitions in game settings or movie scenes. To tackle the challenge of converting backend data into music description texts for audio generation models, MetaBGM employs a novel two-stage generation approach that transforms continuous scene and user state data into these texts, which are then fed into an audio generation model for real-time soundtrack creation. Experimental results demonstrate that MetaBGM effectively generates contextually relevant and dynamic background music for interactive applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03844 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization Liu, Haoxuan Wang, Zihao Hong, Haorong Feng, Youwei Yu, Jiaxin Diao, Han Xu, Yunfei Zhang, Kejun Sound Artificial Intelligence Human-Computer Interaction Multimedia Audio and Speech Processing This paper introduces MetaBGM, a groundbreaking framework for generating background music that adapts to dynamic scenes and real-time user interactions. We define multi-scene as variations in environmental contexts, such as transitions in game settings or movie scenes. To tackle the challenge of converting backend data into music description texts for audio generation models, MetaBGM employs a novel two-stage generation approach that transforms continuous scene and user state data into these texts, which are then fed into an audio generation model for real-time soundtrack creation. Experimental results demonstrate that MetaBGM effectively generates contextually relevant and dynamic background music for interactive applications. |
| title | MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization |
| topic | Sound Artificial Intelligence Human-Computer Interaction Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.03844 |