发表机构
Centre of Research, Experimentation and Production; SCEMI, University of Ngaoundere; Stellenbosch Institute for Advanced Study; Wallenberg Research Centre at Stellenbosch University（研究、实验与生产中心; 恩冈代雷大学SCEMI; 斯泰伦博斯高等研究院; 斯泰伦博斯大学瓦伦贝格研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对非洲低资源语言，提出“模型即库”架构，将社区注册的小型语音模型作为设备端依赖，实现离线、无幻觉的结构化数据收集，并提议转译现有数字表单以支持语音优先采集。
AI 中文摘要
大型语言模型常被提议作为为非洲社区提供AI驱动服务的途径，但它们在需求最迫切的地方恰恰最不可靠：所有非洲语言按任何标准衡量仍属低资源，且基于抓取和标准化文本训练的模型系统性地歪曲了人们实际说话时的方言和地区差异。我们提出“模型即库（Model as a Library, MaaL）”，一种软件架构，将小型、社区注册的语音模型打包为版本化的设备端依赖项，实现无法生成性幻觉的离线结构化数据收集，服务于当前语言模型服务最差的人群。MaaL不依赖网络抓取语料库，其词汇在部署时由说话者本人直接从少量示例录音中注册。我们描述了该架构及其核心机制——关键词 spotting，将封闭词汇文本形式转化为语音形式，并完全在设备端填写和提交——并提议将广泛部署的数字表单工具中已有的封闭词汇元素转译为MaaL模式，为这些工具已覆盖的低识字率人群提供一条低摩擦的、语音优先的离线数据收集路径。这是一篇立场与系统设计论文：我们描述了概念、机制和分析可行性案例，并指出现有实现仍需什么。
英文摘要
Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the need is greatest: all African languages remain low-resource by any standard measure, and models trained on scraped, standardised text systematically misrepresent the dialectal and regional variation of how people actually speak. We introduce \textbf{Model as a Library (MaaL)}, a software architecture that packages small, community-enrolled speech models as versioned on-device dependencies, enabling offline structured data collection that cannot generatively hallucinate, for populations that current language models serve worst. Rather than relying on web-scraped corpora, MaaL's vocabulary is enrolled directly from a small number of example recordings by the speakers themselves, at the point of deployment. We describe the architecture and its central mechanism - keyword spotting that turns a closed-vocabulary text form into a voice form, filled and submitted entirely on-device - and propose transpiling the closed-vocabulary elements already present in widely-deployed digital form tools into MaaL schemas, a low-friction path to voice-first, offline data collection for the low-literacy populations these tools already reach. This is a position and system-design paper: we describe the concept, the mechanism, and an analytical feasibility case, and identify what a working implementation still requires.
Comments5 pages, GlobalSouthAI @ NeurIPS 2026
