Publication result detail

Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion

INAGUMA, H.; CHO, J.; BASKAR, M.; KAWAHARA, T.; WATANABE, S.

Original Title

Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion

English Title

Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion

Type

Paper in proceedings (conference paper)

Original Abstract

This work explores better adaptation methods to low-resource lan-guages using an external language model (LM) under the frame-work of transfer learning. We first build a language-independentASR system in a unified sequence-to-sequence (S2S) architecturewith a shared vocabulary among all languages. During adaptation,we performLM fusion transfer, where an external LM is integratedinto the decoder network of the attention-based S2S model in thewhole adaptation stage, to effectively incorporate linguistic contextof the target language. We also investigate various seed models fortransfer learning. Experimental evaluations using the IARPA BA-BEL data set show that LM fusion transfer improves performanceson all target five languages compared with simple transfer learningwhen the external text data is available. Our final system drasticallyreduces the performance gap from the hybrid systems.

English abstract

This work explores better adaptation methods to low-resource lan-guages using an external language model (LM) under the frame-work of transfer learning. We first build a language-independentASR system in a unified sequence-to-sequence (S2S) architecturewith a shared vocabulary among all languages. During adaptation,we performLM fusion transfer, where an external LM is integratedinto the decoder network of the attention-based S2S model in thewhole adaptation stage, to effectively incorporate linguistic contextof the target language. We also investigate various seed models fortransfer learning. Experimental evaluations using the IARPA BA-BEL data set show that LM fusion transfer improves performanceson all target five languages compared with simple transfer learningwhen the external text data is available. Our final system drasticallyreduces the performance gap from the hybrid systems.

Keywords

end-to-end ASR, multilingual speech recognition,low-resource language, transfer learning

Key words in English

end-to-end ASR, multilingual speech recognition,low-resource language, transfer learning

Authors

INAGUMA, H.; CHO, J.; BASKAR, M.; KAWAHARA, T.; WATANABE, S.

RIV year

2020

Released

12.05.2019

Publisher

IEEE Signal Processing Society

Location

Brighton

ISBN

978-1-5386-4658-8

Book

Proceedings of ICASSP

Pages from

6096

Pages to

6100

Pages count

5

URL

https://ieeexplore.ieee.org/document/8682918

BibTex

@inproceedings{BUT160002,
  author="INAGUMA, H. and CHO, J. and BASKAR, M. and KAWAHARA, T. and WATANABE, S.",
  title="Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion",
  booktitle="Proceedings of ICASSP",
  year="2019",
  pages="6096--6100",
  publisher="IEEE Signal Processing Society",
  address="Brighton",
  doi="10.1109/ICASSP.2019.8682918",
  isbn="978-1-5386-4658-8",
  url="https://ieeexplore.ieee.org/document/8682918"
}

Documents

inaguma_icassp2019_0006096