Effects of Layer Freezing when Transferring DeepSpeech to New Languages

Onno Eberhard, Torsten Zesch

Abstract: In this paper, we investigate the effect of layer freezing on the effectiveness of model transfer in the area of automatic speech recognition. We experiment with Mozilla's DeepSpeech architecture on German and Swiss German speech datasets and compare the results of either training from scratch vs. transferring a pre-trained model. We compare different layer freezing schemes and find that even freezing only one layer already significantly improves results.