构建可自动评估动漫语音风格的偏好框架，突破传统主观评分局限。
AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style
- 通过成对比较收集1.5万条评价，建立偏好式评估体系。
- 声学分析显示动漫感来自共振控制、语调连贯与刻意发音，非单纯高音。
- 基于自监督学习的模型达90.8%准确率，可作生成模型优化奖励信号。
当前动漫语音评估依赖昂贵的主观判断，缺乏标准化客观指标。由于动漫风格无统一绝对尺度，传统均值意见评分（MOS）不可靠。为此，我们提出AnimeScore，一种基于成对排序的偏好式自动评估框架。从187名评价者处收集15,000条成对判断，并附自由描述。声学分析表明，感知动漫感由可控共振塑造、语调连续性及刻意发音驱动，而非简单高音等启发式特征。手工特征模型达69.3% AUC上限，而基于自监督学习的排序模型最高达90.8% AUC，提供实用评估指标，亦可作为生成语音模型偏好优化的奖励信号。
原文摘要 · Abstract (English)
Evaluating 'anime-like' voices currently relies on costly subjective judgments, yet no standardized objective metric exists. A key challenge is that anime-likeness, unlike naturalness, lacks a shared absolute scale, making conventional Mean Opinion Score (MOS) protocols unreliable. To address this gap, we propose AnimeScore, a preference-based framework for automatic anime-likeness evaluation via pairwise ranking. We collect 15,000 pairwise judgments from 187 evaluators with free-form descriptions, and acoustic analysis reveals that perceived anime-likeness is driven by controlled resonance shaping, prosodic continuity, and deliberate articulation rather than simple heuristics such as high pitch. We show that handcrafted acoustic features reach a 69.3% AUC ceiling, while SSL-based ranking models achieve up to 90.8% AUC, providing a practical metric that can also serve as a reward signal for preference-based optimization of generative speech models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。