ST models override masculine ILM biases with acoustic input, using first-person pronouns to link terms to the speaker and accessing gender cues across the full frequency spectrum rather than pitch alone.
What is the impact of the model’s learned knowledge of the target language and a priori assumptions about gender on predictions?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
ST models override masculine ILM biases with acoustic input, using first-person pronouns to link terms to the speaker and accessing gender cues across the full frequency spectrum rather than pitch alone.