谁拿到了麦克风？探究语音大语言模型在说话人分配中的性别偏见
Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
AI总结：
本研究通过分析语音大语言模型Bark的说话人分配来探究性别偏见，构建职业和性别色彩词语两个数据集，发现Bark虽无系统性偏见但具有性别意识和一定倾向。
摘要：
与基于文本的大语言模型（LLMs）类似，语音大语言模型（Speech-LLMs）也表现出涌现能力和上下文感知能力。然而，这些相似性是否延伸到性别偏见仍是一个未解的问题。本研究提出了一种方法，利用说话人分配作为偏见调查的分析工具。与隐式编码性别关联的基于文本的模型不同，语音大语言模型必须生成带有性别特征的声音，这使得说话人选择成为一个显式的偏见线索。我们评估了Bark这一文本转语音（TTS）模型，分析其对文本提示的默认说话人分配。如果Bark的说话人选择系统性地与性别关联一致，则可能揭示其训练数据或模型设计中的模式。为检验这一点，我们构建了两个数据集：（i）Professions，包含具有性别刻板印象的职业，以及（ii）Gender-Colored Words，包含带有性别内涵的词语。虽然Bark并未表现出系统性偏见，但它展现出了性别意识，并具有一定的性别倾向。
英文摘要：
Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology leveraging speaker assignment as an analytic tool for bias investigation. Unlike text-based models, which encode gendered associations implicitly, Speech-LLMs must produce a gendered voice, making speaker selection an explicit bias cue. We evaluate Bark, a Text-to-Speech (TTS) model, analyzing its default speaker assignments for textual prompts. If Bark's speaker selection systematically aligns with gendered associations, it may reveal patterns in its training data or model design. To test this, we construct two datasets: (i) Professions, containing gender-stereotyped occupations, and (ii) Gender-Colored Words, featuring gendered connotations. While Bark does not exhibit systematic bias, it demonstrates gender awareness and has some gender inclinations.
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。
