arXiv Open Access 2025

Different Speech Translation Models Encode and Translate Speaker Gender Differently

Dennis Fucci Marco Gaido Matteo Negri Luisa Bentivogli Andre Martins +1 lainnya
Lihat Sumber

Abstrak

Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. Does this finding also hold for speech translation (ST) models? If so, what are the implications for the speaker's gender assignment in translation? We address these questions from an interpretability perspective, using probing methods to assess gender encoding across diverse ST models. Results on three language directions (English-French/Italian/Spanish) indicate that while traditional encoder-decoder models capture gender information, newer architectures -- integrating a speech encoder with a machine translation system via adapters -- do not. We also demonstrate that low gender encoding capabilities result in systems' tendency toward a masculine default, a translation bias that is more pronounced in newer architectures.

Topik & Kata Kunci

Penulis (6)

D

Dennis Fucci

M

Marco Gaido

M

Matteo Negri

L

Luisa Bentivogli

A

Andre Martins

G

Giuseppe Attanasio

Format Sitasi

Fucci, D., Gaido, M., Negri, M., Bentivogli, L., Martins, A., Attanasio, G. (2025). Different Speech Translation Models Encode and Translate Speaker Gender Differently. https://arxiv.org/abs/2506.02172

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓