NV-Bench：非言语发声合成的基准测试用于表达性文本到语音生成
NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation
AI总结：
本文提出NV-Bench，首个基于功能分类的非言语发声合成基准，包含1651个多语言真实场景语句及人类参考音频，通过双维度评估协议评估TTS模型的可控性和声音真实性。
摘要：
尽管最近的文本到语音（TTS）系统越来越多地整合非言语发声（NVs），但它们的评估缺乏标准化指标和可靠的地面真实参考。为弥合这一差距，我们提出了NV-Bench，首个基于功能分类的基准，将NVs视为交际行为而非声学产物。NV-Bench包含1651个多语言、真实场景语句，配对人类参考音频，平衡14种NV类别。我们引入双维度评估协议：（1）指令对齐，利用提出的语调特征错误率（PCER）评估可控性；（2）声学保真度，测量与真实录音的分布差距以评估声音真实性。我们评估了多种TTS模型并开发了两个基线。实验结果表明，我们的客观指标与人类感知之间存在强相关性，确立NV-Bench为标准化评估框架。
英文摘要：
While recent text-to-speech (TTS) systems increasingly integrate nonverbal vocalizations (NVs), their evaluations lack standardized metrics and reliable ground-truth references. To bridge this gap, we propose NV-Bench, the first benchmark grounded in a functional taxonomy that treats NVs as communicative acts rather than acoustic artifacts. NV-Bench comprises 1,651 multi-lingual, in-the-wild utterances with paired human reference audio, balanced across 14 NV categories. We introduce a dual-dimensional evaluation protocol: (1) Instruction Alignment, utilizing the proposed paralinguistic character error rate (PCER) to assess controllability, (2) Acoustic Fidelity, measuring the distributional gap to real recordings to assess acoustic realism. We evaluate diverse TTS models and develop two baselines. Experimental results demonstrate a strong correlation between our objective metrics and human perception, establishing NV-Bench as a standardized evaluation framework.
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。
