发表机构
Northwestern Polytechnical University; Shanghai Lingguang Zhaxian Technology; Nanjing University（西北工业大学; 上海灵光乍现科技公司; 南京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对非语言发声时间定位监督不足的问题，提出NVV-Locator，通过统一类别、构建时间戳监督数据及非自回归槽填充架构，在基准上取得最优性能并展现跨语料库泛化能力。
AI 中文摘要
人类语音包含非语言发声（NVV），如笑声、叹息、呼吸和咳嗽，这些声音传达情感和互动信息。现有方法通常将NVV表示为转录级别的标签，对其波形时间边界的监督有限。我们提出了NVV-Locator，用于细粒度的NVV时间定位。我们首先统一了公共资源中的26个NVV类别，并通过双LLM验证、转录引导的强制对齐和基于能量的边界细化，构建了大规模时间戳监督的训练数据。我们还引入了NVV-TimeBench，一个经过专家精炼的基准，包含667个话语和1,094个事件。NVV-Locator采用非自回归槽填充架构，联合预测词汇时间戳、NVV类别和事件边界。在NVV-TimeBench上，它达到了71.0%的Micro F1、70.2%的Macro F1、80.4%的Macro mIoU和59.6毫秒的Macro mMAE，优于所评估的大型音频模型对应方法。在外部语料库上的评估进一步证明了NVV-Locator的跨语料库泛化能力。
英文摘要
Human speech includes nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, which convey affective and interactional information. Existing approaches typically represent NVVs as transcript-level tags, providing limited supervision for their waveform-time boundaries. We present NVV-Locator for fine-grained NVV temporal grounding. We first unify 26 NVV categories across public resources and construct large-scale timestamp-supervised training data through dual-LLM verification, transcript-guided forced alignment, and energy-based boundary refinement. We further introduce NVV-TimeBench, an expert-refined benchmark with 667 utterances and 1,094 events. NVV-Locator uses a non-autoregressive slot-filling architecture to jointly predict lexical timestamps, NVV categories, and event boundaries. On NVV-TimeBench, it achieves 71.0% Micro F1, 70.2% Macro F1, 80.4% Macro mIoU, and 59.6 ms Macro mMAE, outperforming the evaluated large audio model counterparts. Evaluation on an external corpus further demonstrates the cross-corpus generalization of NVV-Locator.
