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

• URL: http://arxiv.org/abs/2605.19833v1
• Date: Tue, 19 May 2026 13:26:51 GMT
• Title: Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
• Abstract summary: Mega-ASR combines scalable compound-data construction with progressive acoustic-to-semantic optimization.<n>We show Mega-ASR achieves significant advantages over prior state-of-the-art systems on adverse-condition ASR benchmarks.
• Score: 78.39988331831077
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment [0.0]
  We introduce Lipi-Ghor-882, a comprehensive 882-hour multi-speaker Bengali dataset.<n>For ASR, we demonstrate that raw data scaling is ineffective; instead, targeted fine-tuning utilizing perfectly aligned annotations paired with synthetic acoustic degradation.<n>For speaker diarization, we observed that global open-source state-of-the-art models performed surprisingly poorly on this complex dataset.
  arXiv  Detail & Related papers  (2026-02-26T14:59:24Z)
• When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems [0.6158894274166716]
  Speech enhancement methods are commonly believed to improve the performance of automatic speech recognition (ASR) in noisy environments.<n>We present a systematic evaluation of MetricGAN-plus-voicebank denoising on four state-of-the-art ASR systems.<n>Our results reveal a counterintuitive finding: speech enhancement preprocessing degrades ASR performance across all noise conditions and models.
  arXiv  Detail & Related papers  (2025-12-19T13:32:19Z)
• Cocktail-Party Audio-Visual Speech Recognition [58.222892601847924]
  This study introduces a novel audio-visual cocktail-party dataset designed to benchmark current AVSR systems.<n>We contribute a 1526-hour AVSR dataset comprising both talking-face and silent-face segments, enabling significant performance gains in cocktail-party environments.<n>Our approach reduces WER by 67% relative to the state-of-the-art, reducing WER from 119% to 39.2% in extreme noise, without relying on explicit segmentation cues.
  arXiv  Detail & Related papers  (2025-06-02T19:07:51Z)
• Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation [18.678742816040856]
  Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set.<n>We examine how linguistic and acoustic diversity in training data affect the robustness of the ASR model.<n>We find that targeted acoustic augmentation methods could significantly improve the generalization ability of ASR models.
  arXiv  Detail & Related papers  (2025-05-27T00:55:32Z)
• Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription [18.151884620928936]
  State-of-the-art end-to-end speaker-attributed automatic speech recognition (SA-ASR) architectures lack a multichannel noise and reverberation reduction front-end.<n>We introduce a joint beamforming and SA-ASR approach for real meeting transcription.
  arXiv  Detail & Related papers  (2024-10-29T08:17:31Z)
• Efficient Autoregressive Audio Modeling via Next-Scale Prediction [52.663934477127405]
  We analyze the token length of audio tokenization and propose a novel textbfScale-level textbfAudio textbfTokenizer (SAT)<n>Based on SAT, a scale-level textbfAcoustic textbfAutotextbfRegressive (AAR) modeling framework is proposed, which shifts the next-token AR prediction to next-scale AR prediction.
  arXiv  Detail & Related papers  (2024-08-16T21:48:53Z)
• Convoifilter: A case study of doing cocktail party speech recognition [59.80042864360884]
  The model can decrease ASR's word error rate (WER) from 80% to 26.4% through this approach. We openly share our pre-trained model to foster further research hf.co/nguyenvulebinh/voice-filter.
  arXiv  Detail & Related papers  (2023-08-22T12:09:30Z)
• Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora [70.46867541361982]
  We consider a general non-semantic speech representation, which is trained with a self-supervised criteria based on triplet loss called TRILL. We observe +5.42% and +3.18% relative WER improvement for the development and evaluation sets of Fearless Steps.
  arXiv  Detail & Related papers  (2021-09-23T00:43:32Z)
• A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification [78.04177357888284]
  We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC) We report an efficient joint framework for low-complexity multi-device ASC, called Acoustic Lottery.
  arXiv  Detail & Related papers  (2021-07-03T16:25:24Z)

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.