Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages
University of Duisburg-Essen（杜伊斯堡-埃森大学）
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
