Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is costly for low-resource languages. Therefore, this paper considers a more extreme case of semi-supervised end-to-end automatic speech recognition where there are limited paired speech-text, unlabeled speech (less than five hours), and abundant external text. Firstly, we observe improved performance by training the model using our previous work on semi-supervised learning "CycleGAN and inter-domain losses" solely with external text. Secondly, we enhance "CycleGAN and inter-domain losses" by incorporating automatic hyperparameter tuning, calling it "enhanced CycleGAN inter-domain losses." Thirdly, we integrate it into the noisy student training approach pipeline for low-resource scenarios. Our experimental results, conducted on six non-English languages from Voxforge and Common Voice, show a 20% word error rate reduction compared to the baseline teacher model and a 10% word error rate reduction compared to the baseline best student model, highlighting the significant improvements achieved through our proposed method.

翻译：采用噪声学生训练的半监督端到端语音识别系统已显著提升性能。然而，该方法需要大量配对语音-文本数据与无标注语音，对低资源语言而言成本高昂。为此，本文研究一种更极端的半监督端到端自动语音识别场景：配对语音-文本数据有限、无标注语音不足五小时，但外部文本资源充足。首先，我们观察到仅使用外部文本数据，通过先前提出的半监督学习方法"CycleGAN与跨域损失"训练模型即可提升性能。其次，我们通过引入自动超参数调优机制增强该方法，将其命名为"增强型CycleGAN跨域损失"。最后，我们将该方法整合至低资源场景下的噪声学生训练流程中。在Voxforge与Common Voice数据集的六种非英语语言上进行的实验表明：相较于基线教师模型，该方法实现了20%的词错误率降低；相较于基线最优学生模型，实现了10%的词错误率降低，凸显了所提方法带来的显著性能提升。