mlsanityData to 7 Oct 2026

MLMA: Towards Multilingual ASR With Mamba-based Architectures

arXiv 2510.18684 ↗First posted 21 Oct 2025cs.CL cs.SDcited by 1

On the map: State-space sequence models (S4, Mamba) → Speech and audio SSMs

Abstract (arXiv)

Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers may offer better scalability and efficiency. In this work, we introduce MLMA (Multilingual Language Modeling with Mamba for ASR), a new approach that leverages the Mamba architecture -- an efficient state-space model optimized for long-context sequence processing -- for multilingual ASR. Using Mamba, MLMA implicitly incorporates language-aware conditioning and shared representations to support robust recognition across diverse languages. Experiments on standard multilingual benchmarks show that MLMA achieves competitive performance compared to Transformer-based architectures. These results highlight Mamba's potential as a strong backbone for scalable, efficient, and accurate multilingual speech recognition.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 34 of its 38 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

34 of 38 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025An Exploration of Mamba for Speech Self-Supervised Models14 Jun
  2. 2025Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models6 Jan
  3. 2024Mamba for Streaming ASR Combined with Unimodal Aggregation30 Sep
  4. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models27 Sep
  5. 2024Rethinking Mamba in Speech Processing by Self-Supervised Models11 Sep
  6. 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis13 Jul
  7. 2024Exploring the Capability of Mamba in Speech Applications24 Jun
  8. 2024Mamba in Speech: Towards an Alternative to Self-Attention21 May
  9. 2024An Investigation of Incorporating Mamba for Speech Enhancement10 May
  10. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation27 Mar

Other references · 24

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  6. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 467
  7. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  8. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
  9. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  10. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
  11. 2023SeamlessM4T: Massively Multilingual & Multimodal Machine Translationcited by 124
  12. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
12 more
  1. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
  2. 2024OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformercited by 74
  3. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 63
  4. 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61
  5. 2024A Survey of Mambacited by 39
  6. 2024OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identificationcited by 34
  7. 2019Analyzing ASR pretraining for low-resource speech-to-text translationcited by 27
  8. 2024ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasetscited by 26
  9. 2024Learn and Don't Forget: Adding a New Language to ASR Foundation Modelscited by 16
  10. 2024Scaling A Simple Approach to Zero-Shot Speech Recognitioncited by 8
  11. 2025Efficient Multilingual ASR Finetuning via LoRA Language Expertscited by 5
  12. 2025FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italiancited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  2. 2024LUPET: Incorporating Hierarchical Information Path into Multilingual ASR
  3. 2025The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge
  4. 2026Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling
  5. 2026Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning
  6. 2024Anatomy of Industrial Scale Multilingual ASR
  7. 2025Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge
  8. 2026Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-Tuning