通过一致性正则化提升非自回归语音识别的准确率与鲁棒性
Align-Consistency: Improving Non-autoregressive and Semi-supervised ASR with Consistency Regularization
- 在帧级假设迭代修正中引入一致性正则化，保持预测稳定性
- 非自回归解码与一致性正则化带来可叠加的准确率提升，相对减少23.7%错误率
- 适用于半监督场景，快速生成伪标签显著提升模型性能
一致性正则化（CR）通过确保输入扰动下的预测稳定，提升了连接时序分类（CTC）的鲁棒性和准确性。本文提出Align-Consistency，一种专为非自回归（non-AR）模型Align-Refine设计的CR扩展方法，该模型通过迭代修正帧级假设实现高效推理。实验表明：在全监督设置下，对基线CTC模型及后续修正步骤同时应用CR至关重要，非自回归解码与一致性正则化的增益具有可叠加性；在半监督设置中，利用快速非自回归解码在无标签数据上生成在线伪标签，进一步优化有监督模型，取得显著性能提升。
原文摘要 · Abstract (English)
Consistency regularization (CR) improves the robustness and accuracy of Connectionist Temporal Classification (CTC) by ensuring predictions remain stable across input perturbations. In this work, we propose Align-Consistency, an extension of CR designed for Align-Refine -- a non-autoregressive (non-AR) model that performs iterative refinement of frame-level hypotheses. This method leverages the speed of parallel inference while significantly boosting recognition performance. The effectiveness of Align-Consistency is demonstrated in two settings. First, in the fully supervised setting, our results indicate that applying CR to both the base CTC model and the subsequent refinement steps is critical, and the accuracy improvements from non-AR decoding and CR are mutually additive. Second, for semi-supervised ASR, we employ fast non-AR decoding to generate online pseudo-labels on unlabeled data, which are used to further refine the supervised model and lead to substantial gains.
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。