Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 8 Feb 2021.
Builds on
9 of 19 references.
References · 9
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
- 2016What makes ImageNet good for transfer learning?cited by 192
- 2017Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systemscited by 31
- 2017Transfer Learning for Speech Recognition on a Budgetcited by 25
- 2019Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarincited by 2
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.
3 papers.