LLM decoders in speech recognition show no racial bias amplification and fewer repetition hallucinations under degradation than Whisper, with audio encoder design mattering more than model scale for fairness and robustness.
Bias in the ear of the listener: Assessing sensitivity in audio language models across linguistic, demographic, and positional variations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition
LLM decoders in speech recognition show no racial bias amplification and fewer repetition hallucinations under degradation than Whisper, with audio encoder design mattering more than model scale for fairness and robustness.