).
Real-voice benchmark reveals model-specific demographic bias in Audio-LLMs
HEAR, built from 87k genuine human recordings of 843 diverse speakers, shows that voice bias is a controllable model property and that personalization instructions consistently worsen disparities.
Independent
Shen Yan · Duc Le · Irina-Elena Veliche
Research Digest··2 min read
The authors introduce HEAR, a large-scale benchmark of 87,105 real human audio samples from 843 demographically diverse participants, designed to measure demographic bias in Audio-LLMs.
Why this paper
Independent
In one line
HEAR is a 87k-sample real-voice, demographically diverse benchmark showing voice bias in Audio-LLMs is model-specific and worsened by personalization.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§