RedVox: Safety and Fairness Gaps in Speech Models Across Languages
Multilingual safety and fairness benchmark for speech models reveals persistent vulnerabilities across languages and naturalistic conditions.
Hugging Face · Daily Papers
·Beatrice Savoldi, Sara Papi
·
·▲ 12 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Beatrice Savoldi, Sara Papi, Wafa Aissa, Matteo Negri, Luisa Bentivogli
- 12 upvotes da comunidade
- Temas: speech-capable models, multilingual safety, fairness benchmark, audio, speech models, naturalistic conditions
Resumo
Resumo original (em inglês), extraído do paper:
Multilingual safety and fairness benchmark for speech models reveals persistent vulnerabilities across languages and naturalistic conditions.Onde ler
// relacionados
Leia também
Blog
SpaceX has an AI device prototype, and it sure sounds phone-ish
Blog
Ashton Kutcher leaving Sound Ventures to launch new VC firm with Morgan Beller
Blog
Building a Multimodal Dataset of Academic Paper for Keyword Extraction
Blog