发表机构
Arm Holdings Israel（Arm Holdings 以色列）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低延迟语音活动检测，提出基于状态空间模型的S4VAD架构，并引入概率框架鲁棒评估语音起始延迟，在保持AUROC的同时实现最低延迟。
AI 中文摘要
语音活动检测（VAD）系统通常使用接收者操作特征曲线下面积（AUROC）等指标进行评估，但这些指标并未考虑时间响应性。然而，对于低延迟应用，准确测量语音起始延迟至关重要。这尤其具有挑战性，因为起始延迟评估会受到噪声和注释时间戳系统性错位的影响。在这项工作中，我们引入了一个概率框架，用于在带噪时间标签下评估VAD起始时间。我们将注释的起始时间视为潜在声学起始时间的带噪观测，并从数据中估计由此产生的差异分布。我们表明，这种方法能够提供更稳定、更鲁棒的算法延迟估计。此外，我们提出了S4VAD，这是首个基于状态空间模型（SSM）的VAD架构。S4VAD支持高效的流式推理，同时直接控制过去声学证据的衰减，从而实现快速响应的语音起始检测。我们评估了多种低延迟架构（包括CNN、Transformer和RNN模型）的VAD起始延迟。我们提出的VAD在保持具有竞争力的AUROC的同时，实现了最低的延迟。
英文摘要
Voice Activity Detection (VAD) systems are commonly evaluated using metrics such as the area under the receiver operating characteristic curve (AUROC), but these metrics do not account for temporal responsiveness. For low-latency applications, however, accurately measuring speech onset delay is essential. This is particularly challenging because onset latency evaluation is affected by noise and systematic misalignment in annotation timestamps. In this work, we introduce a probabilistic framework for evaluating VAD onset time under noisy temporal labels. We model annotated onset times as noisy observations of latent acoustic onsets and estimate the resulting discrepancy distribution from data. We show that this approach provides a more stable and robust estimate of algorithmic latency. In addition, we introduce S4VAD, the first state-space-model-based (SSM-based) VAD architecture. S4VAD supports efficient streaming inference while directly controlling the decay of past acoustic evidence, enabling fast and responsive speech-onset detection. We evaluate VAD onset latency across several low-latency architectures, including CNN, Transformer, and RNN models. Our proposed VAD achieves the lowest latency while maintaining a competitive AUROC.
Comments8 pages, 4 Figure
