ASTAR-NTU solution to AudioMOS Challenge 2025 Track1
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_ | 1866912481043021824 |
|---|---|
| author | Ritter-Gutierrez, Fabian Lin, Yi-Cheng Wei, Jui-Chiang Wong, Jeremy H. M. Chen, Nancy F. Lee, Hung-yi |
| author_facet | Ritter-Gutierrez, Fabian Lin, Yi-Cheng Wei, Jui-Chiang Wong, Jeremy H. M. Chen, Nancy F. Lee, Hung-yi |
| contents | Evaluation of text-to-music systems is constrained by the cost and availability of collecting experts for assessment. AudioMOS 2025 Challenge track 1 is created to automatically predict music impression (MI) as well as text alignment (TA) between the prompt and the generated musical piece. This paper reports our winning system, which uses a dual-branch architecture with pre-trained MuQ and RoBERTa models as audio and text encoders. A cross-attention mechanism fuses the audio and text representations. For training, we reframe the MI and TA prediction as a classification task. To incorporate the ordinal nature of MOS scores, one-hot labels are converted to a soft distribution using a Gaussian kernel. On the official test set, a single model trained with this method achieves a system-level Spearman's Rank Correlation Coefficient (SRCC) of 0.991 for MI and 0.952 for TA, corresponding to a relative improvement of 21.21\% in MI SRCC and 31.47\% in TA SRCC over the challenge baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09904 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ASTAR-NTU solution to AudioMOS Challenge 2025 Track1 Ritter-Gutierrez, Fabian Lin, Yi-Cheng Wei, Jui-Chiang Wong, Jeremy H. M. Chen, Nancy F. Lee, Hung-yi Sound Audio and Speech Processing Evaluation of text-to-music systems is constrained by the cost and availability of collecting experts for assessment. AudioMOS 2025 Challenge track 1 is created to automatically predict music impression (MI) as well as text alignment (TA) between the prompt and the generated musical piece. This paper reports our winning system, which uses a dual-branch architecture with pre-trained MuQ and RoBERTa models as audio and text encoders. A cross-attention mechanism fuses the audio and text representations. For training, we reframe the MI and TA prediction as a classification task. To incorporate the ordinal nature of MOS scores, one-hot labels are converted to a soft distribution using a Gaussian kernel. On the official test set, a single model trained with this method achieves a system-level Spearman's Rank Correlation Coefficient (SRCC) of 0.991 for MI and 0.952 for TA, corresponding to a relative improvement of 21.21\% in MI SRCC and 31.47\% in TA SRCC over the challenge baseline. |
| title | ASTAR-NTU solution to AudioMOS Challenge 2025 Track1 |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.09904 |