Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.02421 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910860568428544 |
|---|---|
| author | Chen, Jiatao Xie, Tianming Tang, Xing Wang, Jing Dong, Wenjing Shi, Bing |
| author_facet | Chen, Jiatao Xie, Tianming Tang, Xing Wang, Jing Dong, Wenjing Shi, Bing |
| contents | In recent years, deep learning has significantly advanced the MIDI domain, solidifying music generation as a key application of artificial intelligence. However, existing research primarily focuses on Western music and encounters challenges in generating melodies for Chinese traditional music, especially in capturing modal characteristics and emotional expression. To address these issues, we propose a new architecture, the Dual-Feature Modeling Module, which integrates the long-range dependency modeling of the Mamba Block with the global structure capturing capabilities of the Transformer Block. Additionally, we introduce the Bidirectional Mamba Fusion Layer, which integrates local details and global structures through bidirectional scanning, enhancing the modeling of complex sequences. Building on this architecture, we propose the REMI-M representation, which more accurately captures and generates modal information in melodies. To support this research, we developed FolkDB, a high-quality Chinese traditional music dataset encompassing various styles and totaling over 11 hours of music. Experimental results demonstrate that the proposed architecture excels in generating melodies with Chinese traditional music characteristics, offering a new and effective solution for music generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02421 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MusicMamba: A Dual-Feature Modeling Approach for Generating Chinese Traditional Music with Modal Precision Chen, Jiatao Xie, Tianming Tang, Xing Wang, Jing Dong, Wenjing Shi, Bing Sound Audio and Speech Processing In recent years, deep learning has significantly advanced the MIDI domain, solidifying music generation as a key application of artificial intelligence. However, existing research primarily focuses on Western music and encounters challenges in generating melodies for Chinese traditional music, especially in capturing modal characteristics and emotional expression. To address these issues, we propose a new architecture, the Dual-Feature Modeling Module, which integrates the long-range dependency modeling of the Mamba Block with the global structure capturing capabilities of the Transformer Block. Additionally, we introduce the Bidirectional Mamba Fusion Layer, which integrates local details and global structures through bidirectional scanning, enhancing the modeling of complex sequences. Building on this architecture, we propose the REMI-M representation, which more accurately captures and generates modal information in melodies. To support this research, we developed FolkDB, a high-quality Chinese traditional music dataset encompassing various styles and totaling over 11 hours of music. Experimental results demonstrate that the proposed architecture excels in generating melodies with Chinese traditional music characteristics, offering a new and effective solution for music generation. |
| title | MusicMamba: A Dual-Feature Modeling Approach for Generating Chinese Traditional Music with Modal Precision |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.02421 |