A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR

• URL: http://arxiv.org/abs/2601.00557v1
• Date: Fri, 02 Jan 2026 04:08:39 GMT
• Title: A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR
• Authors: Yuang Zheng, Yuxiang Mei, Dongxing Xu, Jie Chen, Yanhua Long,
• Abstract summary: Large-scale multilingual ASR (mASR) models such as Whisper achieve strong performance but incur high computational and latency costs.<n>We propose a lightweight and language-agnostic multilingual ASR system based on a CTC architecture with domain adaptation.
• Score: 15.703835740288504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 competitive performance with state-of-the-art two-stage inference methods using only single-pass decoding, significantly improving decoding efficiency for low-resource mASR applications.

Related papers

• LiRA: Linguistic Robust Anchoring for Cross-lingual Large Language Models [16.504397960476584]
  LiRA (Linguistic Robust Anchoring for Large Language Models) is a training framework that improves cross-lingual representations under low-resource conditions.<n>We release a multilingual product retrieval dataset covering five Southeast Asian and two South Asian languages.
  arXiv  Detail & Related papers  (2025-10-16T09:08:24Z)
• Efficient Multilingual ASR Finetuning via LoRA Language Experts [59.27778147311189]
  This paper proposes an efficient finetuning framework for customized multilingual ASR via prepared LoRA language experts based on Whisper.<n>Through LoRA expert fusion or knowledge distillation, our approach achieves better recognition performance on target languages than standard fine-tuning methods.<n> Experimental results demonstrate that the proposed models yield approximately 10% and 15% relative performance gains in language-aware and language-agnostic scenarios.
  arXiv  Detail & Related papers  (2025-06-11T07:06:27Z)
• LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models [89.13128402847943]
  We present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision.<n>LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an LLM-based embedding model optimized for embedding-specific tasks.<n>We introduce a new benchmark encompassing 5 primary embedding tasks, 123 diverse datasets, and coverage across 14 languages.
  arXiv  Detail & Related papers  (2025-01-01T15:43:07Z)
• Efficient Spoken Language Recognition via Multilabel Classification [53.662747523872305]
  We show that our models obtain competitive results while being orders of magnitude smaller and faster than current state-of-the-art methods. Our multilabel strategy is more robust to unseen non-target languages compared to multiclass classification.
  arXiv  Detail & Related papers  (2023-06-02T23:04:19Z)
• LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers [71.76680102779765]
  Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. We propose LAMASSU, a streaming language-agnostic multilingual speech recognition and translation model using neural transducers.
  arXiv  Detail & Related papers  (2022-11-05T04:03:55Z)
• LAE: Language-Aware Encoder for Monolingual and Multilingual ASR [87.74794847245536]
  A novel language-aware encoder (LAE) architecture is proposed to handle both situations by disentangling language-specific information. Experiments conducted on Mandarin-English code-switched speech suggest that the proposed LAE is capable of discriminating different languages in frame-level.
  arXiv  Detail & Related papers  (2022-06-05T04:03:12Z)
• Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval [51.60862829942932]
  We present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. For sentence-level CLIR, we demonstrate that state-of-the-art performance can be achieved. However, the peak performance is not met using the general-purpose multilingual text encoders off-the-shelf', but rather relying on their variants that have been further specialized for sentence understanding tasks.
  arXiv  Detail & Related papers  (2021-01-21T00:15:38Z)
• How Phonotactics Affect Multilingual and Zero-shot ASR Performance [74.70048598292583]
  A Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. We replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer.
  arXiv  Detail & Related papers  (2020-10-22T23:07:24Z)
• Streaming End-to-End Bilingual ASR Systems with Joint Language Identification [19.09014345299161]
  We introduce streaming, end-to-end, bilingual systems that perform both ASR and language identification. The proposed method is applied to two language pairs: English-Spanish as spoken in the United States, and English-Hindi as spoken in India.
  arXiv  Detail & Related papers  (2020-07-08T05:00:25Z)
• Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses [13.976935216584298]
  A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel. We propose an approach that learns and combines acoustic level representations with embeddings estimated on ASR hypotheses. To reduce the processing cost and latency, we exploit a streaming architecture to identify the spoken language early.
  arXiv  Detail & Related papers  (2020-06-01T04:08:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.