Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.17785 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910355850002432 |
|---|---|
| author | Liang, Xia Du, Xingjian Lin, Jiaju Zou, Pei Wan, Yuan Zhu, Bilei |
| author_facet | Liang, Xia Du, Xingjian Lin, Jiaju Zou, Pei Wan, Yuan Zhu, Bilei |
| contents | Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To solve this problem, we propose ByteComposer, an agent framework emulating a human's creative pipeline in four separate steps : "Conception Analysis - Draft Composition - Self-Evaluation and Modification - Aesthetic Selection". This framework seamlessly blends the interactive and knowledge-understanding features of LLMs with existing symbolic music generation models, thereby achieving a melody composition agent comparable to human creators. We conduct extensive experiments on GPT4 and several open-source large language models, which substantiate our framework's effectiveness. Furthermore, professional music composers were engaged in multi-dimensional evaluations, the final results demonstrated that across various facets of music composition, ByteComposer agent attains the level of a novice melody composer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17785 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ByteComposer: a Human-like Melody Composition Method based on Language Model Agent Liang, Xia Du, Xingjian Lin, Jiaju Zou, Pei Wan, Yuan Zhu, Bilei Sound Artificial Intelligence Audio and Speech Processing Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To solve this problem, we propose ByteComposer, an agent framework emulating a human's creative pipeline in four separate steps : "Conception Analysis - Draft Composition - Self-Evaluation and Modification - Aesthetic Selection". This framework seamlessly blends the interactive and knowledge-understanding features of LLMs with existing symbolic music generation models, thereby achieving a melody composition agent comparable to human creators. We conduct extensive experiments on GPT4 and several open-source large language models, which substantiate our framework's effectiveness. Furthermore, professional music composers were engaged in multi-dimensional evaluations, the final results demonstrated that across various facets of music composition, ByteComposer agent attains the level of a novice melody composer. |
| title | ByteComposer: a Human-like Melody Composition Method based on Language Model Agent |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.17785 |