通过双视图自蒸馏提升语音识别在噪声下的鲁棒性，不损失清晰语音性能。
DASH: Dual-View Self-Distillation with Multi-Layer Hidden Representations for Robust Speech Recognition
- 利用清晰与噪声语音的配对视图，通过多层隐藏表示自蒸馏学习一致性
- 在LibriSpeech上实现多种噪声条件下识别率提升，且清晰语音准确率不变
- 无需标签预训练，仅增加约4%训练时间，适合实际部署场景
自动语音识别（ASR）在真实噪声环境下性能下降严重，噪声鲁棒性对实际部署至关重要。监督式噪声增强微调虽常用，但可能导致鲁棒性与清晰度之间的权衡，并过度拟合特定噪声类型，反而损害清晰环境下的识别效果。本文提出DASH，一种自蒸馏框架，通过学习清晰-噪声语音的一致性来提升鲁棒性。DASH从编码器多个层级蒸馏隐藏表示，覆盖从低层声学特征到高层语义信息，并通过最小化清晰与噪声视图原型分配分布间的KL散度来稳定训练。在LibriSpeech数据集上的实验表明，DASH在多种噪声条件下均显著提升识别性能，同时保持清晰语音的准确率，仅需比标准微调额外约4%的时间开销即可完成无标签预训练。
原文摘要 · Abstract (English)
Automatic Speech Recognition (ASR) often degrades in real-world noisy environments, making noise robustness essential for deployment. Supervised noise-augmented fine-tuning is a common remedy, but it can introduce a robustness-clean trade-off and overfit to specific corruptions, degrading recognition in clean conditions. We propose DASH, a self-distillation framework that improves robustness by learning clean--noisy consistency from paired views. DASH distills hidden representations from multiple encoder layers to capture features from low-level acoustics to high-level semantics, and stabilizes training by minimizing KL divergence between prototype assignment distributions of clean and noisy views. Experiments on LibriSpeech show that DASH consistently improves recognition under diverse noisy conditions while preserving clean accuracy, achieved by a label-free pre-training stage with minimal additional overhead (about 4% of fine-tuning time) beyond standard fine-tuning.
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。