FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
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_ | 1866915339592269824 |
|---|---|
| author | Kim, Jongsuk Yu, Jaemyung Kwon, Minchan Kim, Junmo |
| author_facet | Kim, Jongsuk Yu, Jaemyung Kwon, Minchan Kim, Junmo |
| contents | Large-scale ASR models have achieved remarkable gains in accuracy and robustness. However, fairness issues remain largely unaddressed despite their critical importance in real-world applications. In this work, we introduce FairASR, a system that mitigates demographic bias by learning representations that are uninformative about group membership, enabling fair generalization across demographic groups. Leveraging a multi-demographic dataset, our approach employs a gradient reversal layer to suppress demographic-discriminative features while maintaining the ability to capture generalizable speech patterns through an unsupervised contrastive loss. Experimental results show that FairASR delivers competitive overall ASR performance while significantly reducing performance disparities across different demographic groups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10747 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition Kim, Jongsuk Yu, Jaemyung Kwon, Minchan Kim, Junmo Audio and Speech Processing Large-scale ASR models have achieved remarkable gains in accuracy and robustness. However, fairness issues remain largely unaddressed despite their critical importance in real-world applications. In this work, we introduce FairASR, a system that mitigates demographic bias by learning representations that are uninformative about group membership, enabling fair generalization across demographic groups. Leveraging a multi-demographic dataset, our approach employs a gradient reversal layer to suppress demographic-discriminative features while maintaining the ability to capture generalizable speech patterns through an unsupervised contrastive loss. Experimental results show that FairASR delivers competitive overall ASR performance while significantly reducing performance disparities across different demographic groups. |
| title | FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.10747 |