SpeechEQ: 社交感知语音对话模型的情商基准测试
SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models
AI总结：
提出SpeechEQ框架，基于EQ-i 2.0理论构建2265个对话数据集，通过口语情商(SEQ)评分评估语音语言模型在主动多轮对话中的副语言社交线索推理能力，揭示端到端模型存在模态捷径、安全陷阱和上下文遗忘等瓶颈。
摘要：
随着多模态对话系统越来越多地参与口语交互，它们处理副语言社交线索的能力已成为自然人机通信的关键瓶颈。然而，现有的机器情商评估仅通过孤立的文本或被动声学感知来评估推理，忽略了主动多轮对话所需的复杂跨模态推理。我们引入了\ extsc{SpeechEQ}，一个旨在评估语音语言模型（SLMs）社会语言学推理能力的综合框架。该框架包含一个经过验证的数据集，包含2265个对话，涵盖基于EQ-i 2.0理论的15个情商（EQ）子量表，以及一个多轮评估协议，通过我们提出的受人类情商评估启发的口语情商（SEQ）评分来衡量。实验表明，现有的语音情感识别和端到端语音语言模型在通过语音理解和应用副语言线索方面存在局限性。虽然端到端架构优于级联系统，但\ extsc{SpeechEQ}揭示了当前多模态模型仍然受到依赖文本的“模态捷径”、对齐引起的“安全陷阱”和“上下文遗忘”的瓶颈，凸显了实现真正情感感知AI的障碍。我们的基准测试可在此https URL访问，演示页面在此https URL。
英文摘要：
As multimodal conversational systems increasingly engage in spoken interaction, their ability to navigate paralinguistic social cues has become a critical bottleneck for natural human-AI communication. However, existing evaluations of machine emotional intelligence assess reasoning exclusively through isolated text or passive acoustic perception, overlooking the complex cross-modal reasoning required for active, multi-turn dialogue. We introduce \textsc{SpeechEQ}, a comprehensive framework designed to evaluate the sociolinguistic reasoning of Speech-Language Models (SLMs). The framework includes a validated dataset of 2,265 dialogues across 15 Emotional Quotient (EQ) subscales grounded in EQ-i 2.0 theory, along with a multi-turn evaluation protocol measured by our proposed Spoken EQ (SEQ) score inspired by human EQ assessments. Experiments show limitations in how both existing Speech Emotion Recognition and end-to-end Speech-Language Models understand and apply paralinguistic cues through speech. While end-to-end architectures outperform cascaded systems, \textsc{SpeechEQ} reveals that current multimodal models remain bottlenecked by a text-reliant ``modality shortcut,'' an alignment-induced ``safety trap,'' and ``contextual amnesia,'' highlighting the barriers to truly emotionally aware AI. Our benchmark can be accessed at https://huggingface.co/datasets/SpeechEQ/SpeechEQ and demo page at https://binomial14.github.io/speecheq-demo/
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。
