mlsanityData to 14 Oct 2026

Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries

arXiv 2601.18899 ↗First posted 26 Jan 2026cs.CL cs.AI cs.SDcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a pretrained LLM via a lightweight connector. Prior work trains a separate connector per language, overlooking linguistic relatedness. We propose an efficient and novel connector-sharing strategy based on linguistic family membership, enabling one connector per family, and empirically validate its effectiveness across two multilingual LLMs and two real-world corpora spanning curated and crowd-sourced speech. Our results show that family-based connectors reduce parameter count while improving generalization across domains, offering a practical and scalable strategy for multilingual ASR deployment.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

13 of 23 references.

References · 13

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  5. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  6. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  7. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  8. 2024Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forwardcited by 17
  9. 2024AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLMcited by 12
  10. 2020Improved acoustic word embeddings for zero-resource languages using multilingual transfercited by 11
  11. 2025Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languagescited by 7
  12. 2024Zero-resource Speech Translation and Recognition with LLMscited by 6
1 more
  1. 2024Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Textcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026MEUSLI: a Multilingual Projector for LLM-based ASR and Beyondcited by 1
  2. 2026Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMscited by 0