智能手表通过个性化语音检测，帮助听障者实时识别名字并触发震动光提示。
Lumename: Wearable Device for Hearing Impaired with Personalized ML-Based Auditory Detection and Haptic-Visual Alerts
- 用音频调制技术扩增单人数据，生成多性别多年龄的语音样本。
- 在微型设备上实现91.67%准确率，推理速度快且功耗低。
- 适合听障人士日常使用，尤其需快速响应特定语音命令的场景。
据世界卫生组织统计，全球有4.3亿人患有致残性听力损失。对于他们而言，识别如姓名等口头指令极为困难。为解决此问题，本文提出Lumename——一款基于Arduino Nano 33 BLE Sense的可穿戴智能手表，利用设备端机器学习实时检测用户自定义名称，并生成触觉与视觉警报。训练阶段，为克服大规模数据需求，采用创新音频调制技术，从单一用户数据中扩增样本，生成涵盖不同性别和年龄的多样化语音。通过约束随机迭代优化模型架构参数，最终实现低资源、低功耗的TinyML模型，在多种关键词样本上快速推理，且在定制化智能手表上保持91.67%的准确率。
原文摘要 · Abstract (English)
According to the World Health Organization, 430 million people experience disabling hearing loss. For them, recognizing spoken commands such as one's name is difficult. To address this issue, Lumename, a real-time smartwatch, utilizes on-device machine learning to detect a user-customized name before generating a haptic-visual alert. During training, to overcome the need for large datasets, Lumename uses novel audio modulation techniques to augment samples from one user and generate additional samples to represent diverse genders and ages. Constrained random iterations were used to find optimal parameters within the model architecture. This approach resulted in a low-resource and low-power TinyML model that could quickly infer various keyword samples while remaining 91.67\% accurate on a custom-built smartwatch based on an Arduino Nano 33 BLE Sense.
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。