通过模拟真实复杂声学环境，提升语音识别在野外场景的鲁棒性。
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
- 构建大规模复合声学数据集，覆盖7类典型噪声与54种组合场景。
- 在多个极端条件测试集上，词错误率降低超30%，优于现有最佳系统。
- 适合需要高鲁棒性语音识别的工业级应用，如智能客服、车载系统。
尽管自动语音识别（ASR）和大型音频语言模型取得快速进展，真实环境中的鲁棒识别仍受限于“声学鲁棒性瓶颈”：模型在严重且复合的声学畸变下常丧失声学依据，导致漏识或幻觉。本文提出Mega-ASR，一个统一的野外环境语音识别框架，结合可扩展的复合数据构建与渐进式声学-语义优化。引入Voices-in-the-Wild-2M数据集，涵盖7类经典声学现象和54种物理上合理的复合场景，并采用声学-语义渐进式监督微调与双粒度词错误率门控策略优化进行训练。大量实验表明，Mega-ASR在恶劣条件下的语音识别基准测试中显著优于现有最先进系统：在VOiCES R4-B-F上词错误率为45.69%（对比54.01%），在NOIZEUS Sta-0上为21.49%（对比29.34%）。在复杂复合声学场景中，相对词错误率降低超过30%，超越强开源与闭源基线，建立了一套可扩展的野外鲁棒语音识别范式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。