Metraipolis › archive › dc_46e508d91504
LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant — arXiv:2609.30692
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30692
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:10:35.579Z
- SHA-256 of the archived text
3c25a6ac0cc845fde92306f88862b9e545a8018957d315e239e790fdd263012e- Stable URL of this page
https://metraipolis.com/documento/dc_46e508d91504
How to cite
LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant — arXiv:2609.30692 — arXiv (en), https://arxiv.org/abs/2609.30692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46e508d91504 (Metraipolis archive dc_46e508d91504, sha256 3c25a6ac0cc845fde92306f88862b9e545a8018957d315e239e790fdd263012e)
BibTeX
@misc{dc46e508d91504,
title = {LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant — arXiv:2609.30692},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30692},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46e508d91504; sha256 3c25a6ac0cc845fde92306f88862b9e545a8018957d315e239e790fdd263012e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.30692 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:43:06.691Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).