mlsanityData to 7 Oct 2026

Coarse-To-Fine And Cross-Lingual ASR Transfer

arXiv 2109.00916 ↗First posted 2 Sep 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even across languages, e.g., German ASR trained from an English model. We experiment with much less related languages, reusing an English model for Czech ASR. To simplify the transfer, we propose to use an intermediate alphabet, Czech without accents, and document that it is a highly effective strategy. The technique is also useful on Czech data alone, in the style of coarse-to-fine training. We achieve substantial eductions in training time as well as word error rate (WER).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 2 Sep 2021.

Builds on

17 of 27 references.

References · 17

  1. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  3. 2018A Survey on Deep Transfer Learningcited by 417
  4. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  5. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
  6. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  7. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  8. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  9. 2019QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutionscited by 93
  10. 2019Jasper: An End-to-End Convolutional Neural Acoustic Modelcited by 75
  11. 2018Trivial Transfer Learning for Low-Resource Neural Machine Translationcited by 47
  12. 2015Transfer Learning for Speech and Language Processingcited by 35
5 more
  1. 2018Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modelingcited by 34
  2. 2017Transfer Learning for Speech Recognition on a Budgetcited by 25
  3. 2017Towards Language-Universal End-to-End Speech Recognitioncited by 14
  4. 2019State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutionscited by 11
  5. 2020Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognitioncited by 9

Built on by

Not cited yet.