This paper presents Conformer-1, an end-to-end Automatic Speech Recognition
(ASR) model trained on an extensive dataset of 570k hours of speech audio data,
91% of which was acquired from publicly available sources. To achieve this, we
perform Noisy Student Training after generating pseudo-labels for the unlabeled
public data using a strong Conformer RNN-T baseline model. The addition of
these pseudo-labeled data results in remarkable improvements in relative Word
Error Rate (WER) by 11.5% and 24.3% for our asynchronous and realtime models,
respectively. Additionally, the model is more robust to background noise owing
to the addition of these data. The results obtained in this study demonstrate
that the incorporation of pseudo-labeled publicly available data is a highly
effective strategy for improving ASR accuracy and noise robustness.

本论文介绍了 Conformer-1，一种端到端的自动语音识别（ASR）模型，它是在一个包含 570k 小时的语音音频数据的广泛数据集上训练的，其中 91％是从公开来源获取的。通过在未标记的公共数据上使用强大的 Conformer RNN-T 基线模型生成伪标签，我们进行有噪声学生训练。这些伪标记数据的添加使我们的异步和实时模型在相对词错误率（WER）上分别提高了 11.5％和 24.3％。此外，由于添加了这些数据，该模型对背景噪声更具鲁棒性。本研究取得的结果表明，将伪标签的公开可用数据纳入 ASR 精度和噪声鲁棒性的改进中是一种非常有效的策略。