Advancing the Foundation Model for Music Understanding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908477635428352 |
|---|---|
| author | Jiang, Yi Wang, Wei Guo, Xianwen Liu, Huiyun Wang, Hanrui Xu, Youri Gu, Haoqi Xie, Zhongqian Luo, Chuanjiang |
| author_facet | Jiang, Yi Wang, Wei Guo, Xianwen Liu, Huiyun Wang, Hanrui Xu, Youri Gu, Haoqi Xie, Zhongqian Luo, Chuanjiang |
| contents | The field of Music Information Retrieval (MIR) is fragmented, with specialized models excelling at isolated tasks. In this work, we challenge this paradigm by introducing a unified foundation model named MuFun for holistic music understanding. Our model features a novel architecture that jointly processes instrumental and lyrical content, and is trained on a large-scale dataset covering diverse tasks such as genre classification, music tagging, and question answering. To facilitate robust evaluation, we also propose a new benchmark for multi-faceted music understanding called MuCUE (Music Comprehensive Understanding Evaluation). Experiments show our model significantly outperforms existing audio large language models across the MuCUE tasks, demonstrating its state-of-the-art effectiveness and generalization ability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01178 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing the Foundation Model for Music Understanding Jiang, Yi Wang, Wei Guo, Xianwen Liu, Huiyun Wang, Hanrui Xu, Youri Gu, Haoqi Xie, Zhongqian Luo, Chuanjiang Sound Artificial Intelligence Information Retrieval Audio and Speech Processing The field of Music Information Retrieval (MIR) is fragmented, with specialized models excelling at isolated tasks. In this work, we challenge this paradigm by introducing a unified foundation model named MuFun for holistic music understanding. Our model features a novel architecture that jointly processes instrumental and lyrical content, and is trained on a large-scale dataset covering diverse tasks such as genre classification, music tagging, and question answering. To facilitate robust evaluation, we also propose a new benchmark for multi-faceted music understanding called MuCUE (Music Comprehensive Understanding Evaluation). Experiments show our model significantly outperforms existing audio large language models across the MuCUE tasks, demonstrating its state-of-the-art effectiveness and generalization ability. |
| title | Advancing the Foundation Model for Music Understanding |
| topic | Sound Artificial Intelligence Information Retrieval Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.01178 |