Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models
像人类一样听?语音语言模型中的语音象征与感知对齐
机构 * Graduate Institute of Communication Engineering National Taiwan University Taipei, Taiwan ; Graduate Institute of Electrical Engineering National Taiwan University Taipei, Taiwan ; Artificial Intelligence Center of Research Excellence National Taiwan University Taipei, Taiwan
专题命中 其他安全 :alignment(title,abstract);分类 cs.CL
AI总结 研究语音语言模型是否有语音象征倾向,通过真实人类语音录音对比模型与人类数据,发现模型听觉判断与人类感知对齐差,错过声学线索,开放权重模型表现不佳,弱点在语音表示方式。
Comments Submitted to SLT 2026