mlsanityData to 14 Oct 2026

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

arXiv 2605.19833 ↗First posted 19 May 2026cs.SD cs.AI cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains limited by an "acoustic robustness bottleneck": models often lose acoustic grounding and produce omissions or hallucinations under severe, compositional distortions. We propose Mega-ASR, a unified ASR-in-the-wild framework that combines scalable compound-data construction with progressive acoustic-to-semantic optimization. We introduce Voices-in-the-Wild-2M, covering 7 classic acoustic phenomena and 54 physically plausible compound scenarios, and train Mega-ASR with Acoustic-to-Semantic Progressive Supervised Fine-Tuning and Dual-Granularity WER-Gated Policy Optimization. Extensive experiments demonstrate that Mega-ASR achieves significant advantages over prior state-of-the-art systems on adverse-condition ASR benchmarks (45.69% vs. 54.01% on VOiCES R4-B-F, and 21.49% vs. 29.34% on NOIZEUS Sta-0). On complex compositional acoustic scenarios, Mega-ASR further delivers over 30% relative WER reduction against strong open- and closed-source baselines, establishing a scalable paradigm for robust ASR in-the-wild.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

38 of 51 references.

References · 38

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  7. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  8. 2025Qwen3-Omni Technical Reportcited by 497
  9. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  10. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  11. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  12. 2023AudioPaLM: A Large Language Model That Can Speak and Listencited by 343
26 more
  1. 2025Kimi-Audio Technical Reportcited by 222
  2. 2023Pengi: An Audio Language Model for Audio Taskscited by 220
  3. 2024Mini-Omni: Language Models Can Hear, Talk While Thinking in Streamingcited by 210
  4. 2023Listen, Think, and Understandcited by 209
  5. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 197
  6. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 186
  7. 2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 144
  8. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 133
  9. 2026Qwen3-ASR Technical Reportcited by 118
  10. 2024WavLLM: Towards Robust and Adaptive Speech Large Language Modelcited by 109
  11. 2024Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilitiescited by 109
  12. 2025Step-Audio 2 Technical Reportcited by 105
  13. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 95
  14. 2025Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Modelscited by 95
  15. 2024Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognitioncited by 63
  16. 2025Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and ASTcited by 60
  17. 2021Fine-tuning wav2vec2 for speaker recognitioncited by 39
  18. 2018Voices Obscured in Complex Environmental Settings (VOICES) corpuscited by 28
  19. 2024Speech Robust Bench: A Robustness Benchmark For Speech Recognitioncited by 21
  20. 2025Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Modelscited by 21
  21. 2026FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition Systemcited by 16
  22. 2021CrowdSpeech and VoxDIY: Benchmark Datasets for Crowdsourced Audio Transcriptioncited by 9
  23. 2025BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognitioncited by 5
  24. 2022pMCT: Patched Multi-Condition Training for Robust Speech Recognitioncited by 3
  25. 2024Improving Multilingual ASR in the Wild Using Simple N-best Re-rankingcited by 2
  26. 2025Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Audio Interaction Modelcited by 4
  2. 2026VoiceMem: Streaming Dual-Brain Memory for Real-Time Interactioncited by 2
  3. 2026Towards Quantifying Benchmark Optimization in ASR Modelscited by 0
  4. 2026Open-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Renderingcited by 0
  5. 2026AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generationcited by 0