Controlling Contrastive Self-Supervised Learning with Knowledge-Driven Multiple Hypothesis: Application to Beat Tracking
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_ | 1866917049394003968 |
|---|---|
| author | Gagnere, Antonin Essid, Slim Peeters, Geoffroy |
| author_facet | Gagnere, Antonin Essid, Slim Peeters, Geoffroy |
| contents | Ambiguities in data and problem constraints can lead to diverse, equally plausible outcomes for a machine learning task. In beat and downbeat tracking, for instance, different listeners may adopt various rhythmic interpretations, none of which would necessarily be incorrect. To address this, we propose a contrastive self-supervised pre-training approach that leverages multiple hypotheses about possible positive samples in the data. Our model is trained to learn representations compatible with different such hypotheses, which are selected with a knowledge-based scoring function to retain the most plausible ones. When fine-tuned on labeled data, our model outperforms existing methods on standard benchmarks, showcasing the advantages of integrating domain knowledge with multi-hypothesis selection in music representation learning in particular. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25560 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Controlling Contrastive Self-Supervised Learning with Knowledge-Driven Multiple Hypothesis: Application to Beat Tracking Gagnere, Antonin Essid, Slim Peeters, Geoffroy Sound Audio and Speech Processing Ambiguities in data and problem constraints can lead to diverse, equally plausible outcomes for a machine learning task. In beat and downbeat tracking, for instance, different listeners may adopt various rhythmic interpretations, none of which would necessarily be incorrect. To address this, we propose a contrastive self-supervised pre-training approach that leverages multiple hypotheses about possible positive samples in the data. Our model is trained to learn representations compatible with different such hypotheses, which are selected with a knowledge-based scoring function to retain the most plausible ones. When fine-tuned on labeled data, our model outperforms existing methods on standard benchmarks, showcasing the advantages of integrating domain knowledge with multi-hypothesis selection in music representation learning in particular. |
| title | Controlling Contrastive Self-Supervised Learning with Knowledge-Driven Multiple Hypothesis: Application to Beat Tracking |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.25560 |