3 papers
cs.CL2025
Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
Lina Conti, Dennis Fucci, Marco Gaido +3
Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns. For example, in spe…
cs.CL2025
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Lina Conti, Dennis Fucci, Marco Gaido +3
Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative…
cs.CL2023
Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models
Lina Conti, Guillaume Wisniewski
Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards…