# The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs

arXiv: https://arxiv.org/abs/2603.16941 · HTML: https://mlsanity.com/paper/2603.16941/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [Recent Advances in Speech Language Models: A Survey](https://mlsanity.com/paper/2410.03751/) (2024)
- [Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation](https://mlsanity.com/paper/1712.01765/) (2017)
- [A Survey on Speech Large Language Models for Understanding](https://mlsanity.com/paper/2410.18908/) (2024)
- [Eliminating Position Bias of Language Models: A Mechanistic Approach](https://mlsanity.com/paper/2407.01100/) (2024)
- [OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM](https://mlsanity.com/paper/2510.15870/) (2025)
- [Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation](https://mlsanity.com/paper/2402.12649/) (2024)
- [MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2502.18924/) (2025)
- [LFM2 Technical Report](https://mlsanity.com/paper/2511.23404/) (2025)
- [The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR](https://mlsanity.com/paper/2303.18110/) (2023)
- [Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models](https://mlsanity.com/paper/2408.07665/) (2024)
- [Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs](https://mlsanity.com/paper/2510.01254/) (2025)
- [Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models](https://mlsanity.com/paper/2310.12049/) (2023)
- [When Voice Matters: Evidence of Gender Disparity in Positional Bias of SpeechLLMs](https://mlsanity.com/paper/2510.02398/) (2025)
- [Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations](https://mlsanity.com/paper/2602.01030/) (2026)

## Built on by (most cited first, 2 of 2)

- [Auditing Bias and Safety in Voice AI Customer Care](https://mlsanity.com/paper/2609.04206/) (2026)
- [Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change](https://mlsanity.com/paper/2609.35922/) (2026)

## Abstract (arXiv)

Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in responses. We present a large-scale intersectional evaluation of accent and gender bias in three SpeechLLMs using 2,880 controlled interactions across six English accents and two gender presentations, keeping linguistic content constant through voice cloning. Using pointwise LLM-judge ratings, pairwise comparisons, and Best-Worst Scaling with human validation, we detect recurring directional disparities. Eastern European-accented speech receives lower helpfulness scores, particularly for female-presenting voices. Responses remain polite but differ in helpfulness. While LLM judges capture the directional trend of these biases, human evaluators exhibit significantly higher sensitivity, showing stronger accent-level contrasts.