用3秒音频预测即将发生的口吃，模型能提前识别严重口吃事件。
Predicting Upcoming Stuttering Events from Three-Second Audio: Stratified Evaluation Reveals Severity-Selective Precursors, and the Model Deploys Fully On-Device
- 基于616K参数的CNN模型，从三秒音频中学习口吃前兆信号。
- 对严重口吃事件预测准确率超0.6，而填充词和重复词无预测能力。
- 模型可部署在设备端，延迟低至0.25毫秒，适合实时干预系统。
现有的语音口吃检测系统多聚焦于当前状态识别，缺乏对后续口吃事件的预测能力。本文在SEP-28k数据集（20,131个三秒片段）上训练了一个616K参数的CNN模型，用于预测下一个连续片段是否包含言语不流畅。实验发现：整体预测性能中等（聚合前导片段AUC=0.581），但按事件类型分层后发现，模型显著偏好临床严重的口吃事件（如停顿块，AUC=0.601；音素重复，AUC=0.617），均显著优于随机水平；而填充词（AUC=0.45）与词重复（AUC=0.49）接近随机。这一现象源于严重事件具有可预测的韵律前兆，而填充词则无。模型在未微调情况下跨人群迁移表现良好，在儿童口吃语料（FluencyBank Teaching，1,024条）上达到0.674（检测）与0.655（预测）的AUC，其他数据集（DisfluencySpeech、LibriStutter）为0.58–0.60。模型可压缩为1.19 MB CoreML或40 KB ONNX格式，运行于iPhone 17 Pro Max的神经引擎时每3秒窗口延迟仅0.25毫秒，四赫兹流式处理占用实时预算的0.54%。校准后输出的测试ECE降至0.010（原为0.177）。五组消融实验（输出级未来引导学习、多片段GRU、时间轴拼接、非对称焦点损失、直接块目标训练）均未超越基础模型。
原文摘要 · Abstract (English)
Audio-based stuttering systems to date have been trained for detection -- what disfluency is present now -- leaving prediction, the capability needed for closed-loop intervention, unstudied at deployable scale. We train a 616K-parameter CNN on SEP-28k (Apple, 20,131 three-second clips) to predict whether the next contiguous clip contains any disfluency. (1) Severity-selective precursor signal: on the episode-grouped test set, aggregate preblock AUC is modest (0.581 [0.542, 0.619]), but stratifying by upcoming event type reveals concentration on clinically severe events -- blocks 0.601 [0.554, 0.651] and sound repetitions 0.617 [0.567, 0.667] both exclude chance, while fillers (0.45) and word repetitions (0.49) are at chance. The aggregate objective converges to a severity-selective predictor because severe events carry prosodic precursors; fillers do not. (2) Cross-population transfer: without fine-tuning, the same checkpoint applied to 1,024 pediatric Children-Who-Stutter utterances (FluencyBank Teaching) attains AUC 0.674 detection and 0.655 prediction; DisfluencySpeech and LibriStutter reach 0.58-0.60 AUC. (3) Deployable on-device: lossless export to CoreML (1.19 MB), ONNX (40 KB), TFLite. Neural-Engine latency per 3 s window: 0.25 ms (iPhone 17 Pro Max, A19 Pro) to 0.55 ms (iPhone SE 3rd-gen and M1 Max). A 4 Hz streaming simulation uses 0.54% of the real-time budget. Platt-calibrated outputs (test ECE 0.010, from 0.177 raw). Five negative ablations -- output-level Future-Guided Learning, multi-clip GRU, time-axis concatenation, asymmetric focal loss, direct block-targeted training -- none improved over the vanilla baseline.
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。