Learning Disentangled Audio Representations through Controlled Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911778318843904 |
|---|---|
| author | Brima, Yusuf Krumnack, Ulf Pika, Simone Heidemann, Gunther |
| author_facet | Brima, Yusuf Krumnack, Ulf Pika, Simone Heidemann, Gunther |
| contents | This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques. Benchmarking state-of-the-art methods on SynTone highlights its utility for method evaluation. Our results underscore strengths and limitations in audio disentanglement, motivating future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10547 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Disentangled Audio Representations through Controlled Synthesis Brima, Yusuf Krumnack, Ulf Pika, Simone Heidemann, Gunther Sound Machine Learning Audio and Speech Processing This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques. Benchmarking state-of-the-art methods on SynTone highlights its utility for method evaluation. Our results underscore strengths and limitations in audio disentanglement, motivating future research. |
| title | Learning Disentangled Audio Representations through Controlled Synthesis |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.10547 |