MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909156411179008 |
|---|---|
| author | Deng, Zihao Ma, Yinghao Liu, Yudong Guo, Rongchen Zhang, Ge Chen, Wenhu Huang, Wenhao Benetos, Emmanouil |
| author_facet | Deng, Zihao Ma, Yinghao Liu, Yudong Guo, Rongchen Zhang, Ge Chen, Wenhu Huang, Wenhao Benetos, Emmanouil |
| contents | Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with a frozen LLM, bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcity of high-quality music Q&A datasets, we created the MusicInstruct (MI) dataset from captions in the MusicCaps datasets, tailored for open-ended music inquiries. Empirical evaluations demonstrate its competitive performance in generating music captions and composing music-related Q&A pairs. Our introduced dataset enables notable advancements beyond previous ones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_08730 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response Deng, Zihao Ma, Yinghao Liu, Yudong Guo, Rongchen Zhang, Ge Chen, Wenhu Huang, Wenhao Benetos, Emmanouil Audio and Speech Processing Artificial Intelligence Computation and Language Multimedia Sound Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with a frozen LLM, bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcity of high-quality music Q&A datasets, we created the MusicInstruct (MI) dataset from captions in the MusicCaps datasets, tailored for open-ended music inquiries. Empirical evaluations demonstrate its competitive performance in generating music captions and composing music-related Q&A pairs. Our introduced dataset enables notable advancements beyond previous ones. |
| title | MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response |
| topic | Audio and Speech Processing Artificial Intelligence Computation and Language Multimedia Sound |
| url | https://arxiv.org/abs/2309.08730 |