In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end speech recognition model. Without any extra loss function, we utilize the Gradient Mask to optimize the model when training on pseudo-label. This method forces the speech recognition model to predict from the masked input to learn strong acoustic representation and make training robust to label noise. In our semi-supervised experiments, the method can improve the model performance when training on pseudo-label and our method achieved competitive results comparing with other semi-supervised approaches on the Librispeech 100 hours experiments.
翻译:在最近半监督的语音识别趋势中,自我监督的代言学习和假标签学习都显示出了有希望的结果。 在本文中,我们提出了一种新颖的方法来结合他们关于端到端语音识别模式的想法。在没有额外的损失功能的情况下,我们利用渐变面罩来优化假标签培训模式。这种方法迫使语音识别模型从蒙面输入中预测,学习强大的声学代表,并使培训对噪音进行有力标记。 在我们的半监督的实验中,当伪标签和我们的方法培训取得与Librispeech 100小时试验的其他半监督方法相比的竞争结果时,这种方法可以改进模型性能。