arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.20743eess.SPcs.SD
收藏

绑定效应:分析多维线索如何在指令文本到语音中形成性别偏见

The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS

Graduate Institute of Communication Engineering, National Taiwan University, Taiwan(台湾大学通讯工程研究所);AI Research Center, Inventec Corporation, Taiwan(Inventec公司人工智能研究中心)

Kuan-Yu Chen, Yi-Cheng Lin, Po-Chung Hsieh, Huang-Cheng Chou, Chih-Fan Hsu, Jeng-Lin Li, Hung-yi Lee, Jian-Jiun Ding

AI总结:

研究通过分析多维线索的交互作用,揭示了指令文本到语音中性别偏见的复杂模式,指出单一维度测试无法全面捕捉偏见,强调需进行组合分析以识别生成语音中的潜在风险。

摘要:

当前指令文本到语音(ITTS)中的偏见评估往往依赖于单变量测试,忽略了社会线索的组成结构。在本工作中,我们通过将提示建模为社会地位、职业刻板印象和人物描述的组合,研究了性别偏见。通过分析开源ITTS模型,我们发现系统交互效应,其中社会维度相互调节,产生复杂的偏见模式,这被单变量基线所遗漏。关键发现表明,这些偏见不仅限于表层 artifacts,还与预训练文本编码器的语义先验和训练数据中的偏分布有强关联。我们进一步证明,通用多样性提示不足以克服这些根深蒂固的模式,强调了进行组合分析以诊断生成语音中潜在风险的必要性。

英文摘要:

Current bias evaluations in Instruction Text-to-Speech (ITTS) often rely on univariate testing, overlooking the compositional structure of social cues. In this work, we investigate gender bias by modeling prompts as combinations of Social Status, Career stereotypes, and Persona descriptors. Analyzing open-source ITTS models, we uncover systematic interaction effects where social dimensions modulate one another, creating complex bias patterns missed by univariate baselines. Crucially, our findings indicate that these biases extend beyond surface-level artifacts, demonstrating strong associations with the semantic priors of pre-trained text encoders and the skewed distributions inherent in training data. We further demonstrate that generic diversity prompting is insufficient to override these entrenched patterns, underscoring the need for compositional analysis to diagnose latent risks in generative speech.

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。

↑