arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05065eess.AS
收藏

Emo-bias:语音情感识别中社会偏见的大规模评估

Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition

National Taiwan University(国立台湾大学);National Tsing Hua University(国立清华大学)

Yi-Cheng Lin, Haibin Wu, Huang-Cheng Chou, Chi-Chun Lee, Hung-yi Lee

AI总结:

该研究针对语音情感识别模型可能存在的性别社会偏见问题,从上游模型和数据两方面大规模分析自监督学习训练的SER模型的性别偏见,发现情感分布差异对偏见影响显著,上游表征影响有限。

摘要:

语音情感识别(Speech Emotion Recognition, SER)的快速发展在全球范围内有着多样应用,从改善人机交互到辅助心理健康诊断。然而,SER模型可能存在针对性别的社会偏见,导致不公平结果。本研究大规模分析了采用自监督学习(Self-Supervised Learning, SSL)训练的SER模型中的性别偏见,探究其影响因素。选择基于SSL的SER模型是因为其性能处于前沿水平。本研究首次从上游模型和数据两个视角研究SER中的性别偏见。研究结果显示,女性的整体SER表现略高于男性。两种知名SSL模型——改进版CPC和XLS-R——表现出显著偏见。此外,用普通话数据集训练的模型在效价维度上存在明显偏见。最后,我们发现训练数据中按性别划分的情感分布差异对性别偏见有显著影响,而上流模型表征的影响较为有限。

英文摘要:

The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics. However, SER models might contain social bias toward gender, leading to unfair outcomes. This study analyzes gender bias in SER models trained with Self-Supervised Learning (SSL) at scale, exploring factors influencing it. SSL-based SER models are chosen for their cutting-edge performance. Our research pioneering research gender bias in SER from both upstream model and data perspectives. Our findings reveal that females exhibit slightly higher overall SER performance than males. Modified CPC and XLS-R, two well-known SSL models, notably exhibit significant bias. Moreover, models trained with Mandarin datasets display a pronounced bias toward valence. Lastly, we find that gender-wise emotion distribution differences in training data significantly affect gender bias, while upstream model representation has a limited impact.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑