AI RESEARCH
A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR
arXiv CS.CL
•
ArXi:2601.00557v2 Announce Type: replace Large-scale multilingual ASR (mASR) models such as Whisper achieve strong performance but incur high computational and latency costs, limiting their deployment on resource-constrained edge devices. In this study, we propose a lightweight and language-agnostic multilingual ASR system based on a CTC architecture with domain adaptation. Specifically, we