用联邦学习保护隐私，实现抗噪、省带宽的婴儿哭声分类。
Privacy-Enhancing Infant Cry Classification with Federated Transformers and Denoising Regularization
- 融合去噪自编码器与联邦Transformer，支持本地去噪和边缘推理。
- 在双数据集上达0.938宏F1、0.962 AUC，校准误差仅0.032。
- 客户端上传量从约42MB降至3.3MB，适合低资源设备实时部署。
婴儿哭声分类有助于早期评估婴儿需求。然而，音频数据的隐私顾虑、对背景噪声的敏感性以及不同录制环境下的领域偏移限制了此类方案的部署。本文提出一个端到端婴儿哭声分析流程，集成去噪自编码器（DAE）、卷积分词器和使用通信高效的联邦学习（FL）训练的Transformer编码器。系统支持本地去噪、自适应分割、事后校准及基于能量的分布外（OOD）拒识。联邦训练采用带正则化控制变差更新，在安全聚合下使用8位适配器增量。在Baby Chillanto与Donate-a-Cry数据集上叠加ESC-50噪声，模型取得0.938宏F1、0.962 AUC和0.032预期校准误差（ECE），每轮客户端上传量从约36–42 MB降至3.3 MB。在NVIDIA Jetson Nano（4 GB，TensorRT FP16）上实现每秒1秒频谱帧96毫秒的实时边缘推理。结果表明，该方法为隐私保护、抗噪且通信高效的小儿哭声分类提供了可行路径。
原文摘要 · Abstract (English)
Infant cry classification can aid early assessment of infant needs. However, deployment of such solutions is limited by privacy concerns around audio data, sensitivity to background noise, and domain shift across recording environments. We present an end-to-end infant cry analysis pipeline that integrates a denoising autoencoder (DAE), a convolutional tokenizer, and a Transformer encoder trained using communication-efficient federated learning (FL). The system performs on-device denoising, adaptive segmentation, post hoc calibration, and energy-based out-of-distribution (OOD) abstention. Federated training employs a regularized control variate update with 8-bit adapter deltas under secure aggregation. Using the Baby Chillanto and Donate-a-Cry datasets with ESC-50 noise overlays, the model achieves a macro F1 score of 0.938, an AUC of 0.962, and an Expected Calibration Error (ECE) of 0.032, while reducing per-round client upload from approximately 36 to 42 MB to 3.3 MB. Real-time edge inference on an NVIDIA Jetson Nano (4 GB, TensorRT FP16) achieves 96 ms per one-second spectrogram frame. These results demonstrate a practical path toward privacy-preserving, noise-robust, and communication-efficient infant cry classification suitable for federated deployment.
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。