arXiv AI September 11, 2026 By Xiaoqun Liu, Tanu Mitra, Harshit Rajgarhia, Abhishek Mukherji

Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models

The study investigates how speech‑to‑speech (S2S) models handle gender, distinguishing between the acoustic voice and the content’s gender cues. Experiments across five models in English, Spanish, and Mandarin show that while the rendered voice remains unbiased, the models consistently attribute speaker gender based on textual content rather than voice. When content and voice disagree, misgendering rates soar to 90%, whereas agreement yields only 2% misgendering.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 1

Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias

arXiv:2502.10577v2 Announce Type: replace-cross Abstract: Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constra...

By Enzo Doyen, Amalia Todirascu

llms safety

arXiv AI

Jun 2

Failure of contextual invariance in large language models

arXiv:2603. 23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent discourses.

By Sagar Kumar, Ariel Flint, Luca Maria Aiello, Andrea Baronchelli

llms benchmarks safety

arXiv Computation and Language

Oct 16

Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

The paper presents methods to reduce gender bias in audio‑enabled large language models (AuLLMs) by using adversarial training to unlearn gender perception without harming performance on other tasks. It also introduces a distillation approach that retains gender awareness but aligns responses with a gender‑agnostic teacher unless explicitly prompted. Experiments on three AuLLMs show promising results for gender‑unlearning and partial success for the distillation technique.

By Adnan Al Ali, Jind\v{r}ich Libovick\'y, Anne Lauscher

llms efficiency safety

arXiv Computer Vision

Sep 17

Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plan

arXiv:2609.17913v1 Announce Type: new Abstract: Face--voice association models may rely on language or gender cues in the voice rather than on speaker-specific voice characteristics, which can lead t...

By Marta Moscati, Swapnil Khandoker, Muhammad Saad Saeed, Shah Nawaz, Fatima Noor, Rohan Kumar Das, Mubashir Noman, Junaid Mir, Muhammad Haroon Yousaf, Khalid Malik, Markus Schedl

multimodal benchmarks

arXiv Computation and Language

Oct 19

Analyzing Occupational Gender Bias across the LLM Training Lifecycle

arXiv:2610.23587v1 Announce Type: new Abstract: Post-training is widely assumed to reduce the social biases language models inherit from pretraining, yet direct evidence for this assumption remains m...

By Manthan Gadhia, Alexander Hoyle, Karolina Sta\'nczak

llms reinforcement-learning fine-tuning safety

Hugging Face Trending Papers

Sep 15

Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plan

Face--voice association models may rely on language or gender cues in the voice rather than on speaker-specific voice characteristics, which can lead to a performance deterioration when the model has...

multimodal benchmarks

One email a morning, machine-written

Related stories

Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias

Failure of contextual invariance in large language models

Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plan

Analyzing Occupational Gender Bias across the LLM Training Lifecycle

Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plan