VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
arXiv preprint arXiv:2508.21376 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
The paper delivers a unified framework for fairness in speech technologies by formalizing seven definitions, organizing research into three paradigms, diagnosing pipeline-specific biases, and mapping mitigations to those sources.
Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unresolved attribution after separation.
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
VIBE evaluates generative biases in large audio-language models with real-world speech and open-ended tasks, showing that gender cues produce larger distributional shifts than accent cues across 11 tested models.
AU-Harness introduces an efficient unified evaluation framework for audio LLMs featuring batch optimizations, multi-turn dialogue support, and standardized protocols for fair comparisons.
citing papers explorer
-
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
-
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
The paper delivers a unified framework for fairness in speech technologies by formalizing seven definitions, organizing research into three paradigms, diagnosing pipeline-specific biases, and mapping mitigations to those sources.
-
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unresolved attribution after separation.
-
AudioMosaic: Contrastive Masked Audio Representation Learning
AudioMosaic learns general-purpose audio representations through contrastive pre-training with structured spectrogram masking, reaching state-of-the-art results on standard benchmarks and improving audio-language tasks.
-
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
VIBE evaluates generative biases in large audio-language models with real-world speech and open-ended tasks, showing that gender cues produce larger distributional shifts than accent cues across 11 tested models.
-
AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs
AU-Harness introduces an efficient unified evaluation framework for audio LLMs featuring batch optimizations, multi-turn dialogue support, and standardized protocols for fair comparisons.