SDiaReward：基于模态和口语性的语音对话奖励建模与基准测试
SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
AI总结：
本文提出SDiaReward，一种端到端的多轮奖励模型，通过SDiaReward-Dataset数据集解决模态和口语性差距问题，实现对语音对话中模态和口语性的联合评估，实验表明其在配对偏好准确率上优于通用音频大语言模型。
摘要：
端到端语音对话系统的发展需要超越单纯文本语义，融入语调和情感等非语言特征以及人类对话的自发性。然而，当前方法面临两个关键缺口：模态缺口（涉及语调和情感）和口语性缺口（区分书面脚本与自然口语）。为此，我们引入SDiaReward，一种基于SDiaReward-Dataset训练的端到端多轮奖励模型，该数据集专门针对这些缺口收集了篇章级偏好对。SDiaReward直接在完整的多轮语音篇章上运行，并通过配对偏好监督进行优化，实现对模态和口语性的联合评估。我们进一步建立了ESDR-Bench，一个分层的基准测试，用于鲁棒的篇章级评估。实验表明，SDiaReward在配对偏好准确率上达到最先进的水平，显著优于通用音频大语言模型。进一步分析表明，SDiaReward能够捕捉超越表面合成线索的相对对话表达性，提高跨领域和录音条件的泛化能力。代码、数据和演示可在https://github.com/MM-Speech/SDiaReward/上获得。
英文摘要：
The rapid evolution of end-to-end spoken dialogue systems demands transcending mere textual semantics to incorporate paralinguistic nuances and the spontaneous nature of human conversation. However, current methods struggle with two critical gaps: the modality gap, involving prosody and emotion, and the colloquialness gap, distinguishing written scripts from natural speech. To address these challenges, we introduce SDiaReward, an end-to-end multi-turn reward model trained on SDiaReward-Dataset, a novel collection of episode-level preference pairs explicitly targeting these gaps. It operates directly on full multi-turn speech episodes and is optimized with pairwise preference supervision, enabling joint assessment of modality and colloquialness in a single evaluator. We further establish ESDR-Bench, a stratified benchmark for robust episode-level evaluation. Experiments demonstrate that SDiaReward achieves state-of-the-art pairwise preference accuracy, significantly outperforming general-purpose audio LLMs. Further analysis suggests that SDiaReward captures relative conversational expressiveness beyond superficial synthesis cues, improving generalization across domains and recording conditions. Code, data, and demos are available at https://github.com/MM-Speech/SDiaReward/.
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。
