弱监督语音识别新模型，能抗高达70%的文本错误。
WST: Weakly Supervised Transducer for Automatic Speech Recognition
- 设计灵活训练图，无需额外置信度估计即可应对转录错误。
- 在70%转录错误率下仍保持性能，优于现有CTC方法。
- 适合真实场景中数据质量差的语音识别任务。
端到端语音识别广泛采用循环神经网络-变换器（RNN-T），但其严重依赖大规模高质量标注数据，而这些数据往往成本高且难以获取。为缓解这一问题，本文提出弱监督变换器（WST），通过设计一种灵活的训练图结构，能够稳健处理转录错误，且无需额外的置信度估计或预训练辅助模型。在合成与工业数据集上的实证评估表明，当转录错误率高达70%时，WST仍能有效维持性能，持续优于现有的基于连接时序分类（CTC）的弱监督方法，如绕过时序分类（BTC）和全时序分类（OTC）。结果证明了WST在真实语音识别场景中的实用性和鲁棒性。代码将公开发布。
原文摘要 · Abstract (English)
The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain. To mitigate this reliance, we propose a Weakly Supervised Transducer (WST), which integrates a flexible training graph designed to robustly handle errors in the transcripts without requiring additional confidence estimation or auxiliary pre-trained models. Empirical evaluations on synthetic and industrial datasets reveal that WST effectively maintains performance even with transcription error rates of up to 70%, consistently outperforming existing Connectionist Temporal Classification (CTC)-based weakly supervised approaches, such as Bypass Temporal Classification (BTC) and Omni-Temporal Classification (OTC). These results demonstrate the practical utility and robustness of WST in realistic ASR settings. The implementation will be publicly available.
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。