{"ID":2823194,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00557","arxiv_id":"2601.00557","title":"A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR","abstract":"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 introduce a Language-agnostic Hierarchical LoRA-MoE (HLoRA) framework integrated into an mHuBERT-CTC model, enabling end-to-end decoding via LID-posterior-driven LoRA routing. The hierarchical design consists of a multilingual shared LoRA for learning language-invariant acoustic representations and language-specific LoRA experts for modeling language-dependent characteristics. The proposed routing mechanism removes the need for prior language identity information or explicit language labels during inference, achieving true language-agnostic decoding. Experiments on MSR-86K and the MLC-SLM 2025 Challenge datasets demonstrate that HLoRA achieves comparable performance to two-stage inference approaches while reducing RTF by 11.7% and 8.2%, respectively, leading to improved decoding efficiency for low-resource mASR applications.","short_abstract":"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 dom...","url_abs":"https://arxiv.org/abs/2601.00557","url_pdf":"https://arxiv.org/pdf/2601.00557v2","authors":"[\"Yuang Zheng\",\"Dongxu Chen\",\"Yuxiang Mei\",\"Dongxing Xu\",\"Jie Chen\",\"Yanhua Long\"]","published":"2026-01-02T04:08:39Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.SD\",\"eess.AS\"]","methods":"[\"LoRA\"]","has_code":false}