Leading AI models are biased against certain accents when scoring interviews, presentations and tests

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

Add to Preferred Sources Credit: ShotPot from Pexels Artificial intelligence models replicate, and sometimes amplify, all sorts of human biases. In the last few years, University of Washington researchers have found AI has erased female characters from kids' stories, favored job applicants of certain races and genders and swayed human decisions.

Much bias research has focused on text and visuals. Yet people speak to AI models with increasing regularity, and AI tools are now used to screen job applicants and score oral presentations. Now, a UW-led team of researchers found that state-of-the-art AI models were biased against speakers with certain accents.

The team investigated how state-of-the-art multimodal language models, including two from Google and one from OpenAI, evaluated human speech in job interviews, conference presentations and spoken English proficiency tests. The models scored responses from voices speaking English with five different accents: American, British, Chinese, Indian and Nigerian.

The AI models generally ranked Chinese and Nigerian accents the lowest, Indian in the middle and American and British the highest. Even when the content was exactly the same and the models could accurately transcribe the speech, the systems ranked both the delivery and content higher for the American and British speakers.

The team presented its research Oct. 25 at the Conference on Empirical Methods in Natural Language Processing in Budapest, Hungary.

"People are now trusting audio AI models as sort of third-party evaluators, for hiring, for oral exams in education, for certain English tests in immigration—contexts where fairness really matters," said co-lead author Orevaoghene Ahia, a UW doctoral student in the Paul G. Allen School of Computer Science & Engineering. "So I was curious how models perceive speech from people who don't speak with so-called 'standard' American accents."

The team chose accents from five regions that have large populations of English speakers and where the researchers also had connections. Researchers then tested the accents in three different domains—hiring, presentations and English tests. To study differences at scale, they had AI voices from ElevenLabs read the same pieces of text to the AI models being tested. They validated the results with 52 human speakers from the five countries.

After some testing, the team focused the study on three proprietary AI models—Google's Gemini 2.5 Pro and Gemini 2.5 Flash, and OpenAI's GPT-Audio 1.5—and one open-source model, Qwen 3 Omni.

"We wanted to check these state-of-the-art models," said senior author Yulia Tsvetkov, a UW associate professor in the Allen School, "because these are what companies would deploy in a real-world setting."

The team had the AI voices read various scripts—interview responses, a class presentation, a conference presentation and English proficiency test responses—with the five different accents in both male and female voices. The four AI models then rated the responses on a scale of 1 to 7 for both delivery and content and gave a brief explanation for their scores.

Researchers repeated the interview response test with the 52 human participants, having them read four scripted responses each and respond to questions without a script.

The results favored American and British accents—with a greater disparity between the human accents than between the AI accents.

To better understand the results, researchers analyzed the acoustic features of the accents. They then measured their "acoustic distance" and found that accents further from Americans' were often ranked lower.

The team found this apparent hierarchy manifested in the models' explanations, too.

"Even though they repeatedly claimed Chinese and Nigerian speakers 'mumbled' or were 'difficult to understand,' the models were actually very good at transcribing the accented speech," Ahia said. "They understood the speakers, but they just had this implicit notion of hierarchy among them based on accent."

This bias can seep into models during training in various ways—possibly through data that describes accented speakers as hard to understand, through data sets that underrepresent certain populations and accents, or through training methods that reinforce conventional expectations about how a professional speaker should sound. English, for instance, is the official language in Nigeria and is the teaching language in Indian schools, yet both accents were rated lower than British and American.

"One clear direction for future work is to create more representative training and evaluation data sets that could improve the accuracy and fairness of language models," Tsvetkov said.

The team plans to expand the research by studying more human accents—including regional variations within countries—and by looking at how AI models are analyzing audio in medical contexts, such as automated emergency response.

"For all of these, we hope that developers build and publish evaluations of their models that don't focus only on average performance, but also break it down into subpopulations, dialects and so on," Tsvetkov said. "We don't want the average performance to be 97% accurate for the general population, but for a smaller group only 20%."

Aruna Srivastava et al., The Cost of Sounding Different: Accent Bias in Audio Language Models, Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026). DOI: 10.18653/2026.emnlp-main.1612 Key concepts Large language models AI alignment Human-centered AI interfaces Provided by University of Washington Who's behind this story? Robert Egan Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →