发表机构
Jatiya Kabi Kazi Nazrul Islam University（贾蒂亚卡比卡齐纳兹鲁尔伊斯兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对离线环境隐私与延迟问题，提出LUMO，一种集成本地ASR、量化LLM和TTS的完全离线语音助手，在树莓派5上实现低延迟、低功耗及多语言支持。
AI 中文摘要
在互联网连接有限且隐私要求高的环境中，可靠的语音交互至关重要。然而，大多数现有语音助手依赖基于云的服务，这导致延迟问题、对互联网访问的依赖以及隐私漏洞。本研究提出了LUMO（轻量级统一多语言编排器），一种为边缘计算环境设计的隐私保护离线语音助手。该系统将本地自动语音识别（ASR）、本地部署的量化大型语言模型（LLM）和文本到语音（TTS）合成集成到一个完全离线的流水线中，运行在配备8 GB RAM的Raspberry Pi 5上。为了在资源受限的硬件上实现高效运行，语言模型采用4位GGUF量化进行压缩，这减少了内存使用，同时保持了实用的对话能力。现有的基于边缘的语音助手Mycroft提供了部分离线功能，但没有生成式LLM，其近似延迟约为5秒，功耗约为12瓦，而Rhasspy支持完全离线操作，但缺乏生成能力，延迟约为3秒，功耗约为11瓦。相比之下，LUMO在低噪声条件下对短英文话语实现了6.8%的词错误率（WER），端到端响应延迟为2.0-4.0秒，峰值功耗较低，约为9.0瓦。该系统还实现了对孟加拉语语音的有效离线识别，支持低资源环境下的多语言可访问性。通过完全离线运行，LUMO提供了强大的数据隐私，减少了对云连接的需求，并适用于隐私敏感的边缘执行场景，如农村医疗、教育和灾难响应。
英文摘要
Reliable voice interaction is essential in environments with limited internet connectivity and strong privacy. However, most existing voice assistants depend on cloud-based services, which leads to latency issues, dependency on internet access, and privacy vulnerabilities. This research presents LUMO (Lightweight Unified Multilingual Orchestrator), a privacy preserving offline voice assistant designed for edge computing environments. This system integrates local Automatic Speech Recognition (ASR), locally deployed quantized Large Language Model (LLM), and Text-to-Speech (TTS) synthesis into a fully offline pipeline running on a Raspberry Pi 5 with 8 GB RAM. To enable efficient operation on resource constrained hardware, the language model is compressed using 4-bit GGUF quantization, which reduces memory usage while preserving practical conversational capability. Existing edge based voice assistants Mycroft provides partial offline functionality without a generative LLM, with an approximate latency of ~5 s and power consumption of ~12 W, while Rhasspy supports full offline operation but lacks generative capabilities, with ~3 s latency and ~11 W power usage. In contrast, LUMO achieves a Word Error Rate (WER) of 6.8% for short English utterances in low noise conditions, an end-to-end response latency of 2.0-4.0 s, and a lower peak power consumption of approximately 9.0 W. The system also achieves effective offline recognition for Bangla speech, supporting multilingual accessibility in low resource settings. By operating entirely offline, LUMO provides strong data privacy, reduced need for cloud connectivity, and suitability for privacy sensitive edge execution such as rural healthcare, education, and disaster response scenarios.
Comments6 pages, 8 figures, 9 tables. Conference version prepared for IEEE 3rd International Conference on Computing, Applications and Systems (COMPAS 2026), 9-10 October 2026, University of Dhaka, Bangladesh
