Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911037202104320 |
|---|---|
| author | Batlle-Roca, Roser Liao, Wei-Hsiang Serra, Xavier Mitsufuji, Yuki Gómez, Emilia |
| author_facet | Batlle-Roca, Roser Liao, Wei-Hsiang Serra, Xavier Mitsufuji, Yuki Gómez, Emilia |
| contents | Recent advancements in music generation are raising multiple concerns about the implications of AI in creative music processes, current business models and impacts related to intellectual property management. A relevant discussion and related technical challenge is the potential replication and plagiarism of the training set in AI-generated music, which could lead to misuse of data and intellectual property rights violations. To tackle this issue, we present the Music Replication Assessment (MiRA) tool: a model-independent open evaluation method based on diverse audio music similarity metrics to assess data replication. We evaluate the ability of five metrics to identify exact replication by conducting a controlled replication experiment in different music genres using synthetic samples. Our results show that the proposed methodology can estimate exact data replication with a proportion higher than 10%. By introducing the MiRA tool, we intend to encourage the open evaluation of music-generative models by researchers, developers, and users concerning data replication, highlighting the importance of the ethical, social, legal, and economic consequences. Code and examples are available for reproducibility purposes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14364 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio Batlle-Roca, Roser Liao, Wei-Hsiang Serra, Xavier Mitsufuji, Yuki Gómez, Emilia Sound Artificial Intelligence Multimedia Audio and Speech Processing Recent advancements in music generation are raising multiple concerns about the implications of AI in creative music processes, current business models and impacts related to intellectual property management. A relevant discussion and related technical challenge is the potential replication and plagiarism of the training set in AI-generated music, which could lead to misuse of data and intellectual property rights violations. To tackle this issue, we present the Music Replication Assessment (MiRA) tool: a model-independent open evaluation method based on diverse audio music similarity metrics to assess data replication. We evaluate the ability of five metrics to identify exact replication by conducting a controlled replication experiment in different music genres using synthetic samples. Our results show that the proposed methodology can estimate exact data replication with a proportion higher than 10%. By introducing the MiRA tool, we intend to encourage the open evaluation of music-generative models by researchers, developers, and users concerning data replication, highlighting the importance of the ethical, social, legal, and economic consequences. Code and examples are available for reproducibility purposes. |
| title | Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio |
| topic | Sound Artificial Intelligence Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.14364 |