Detail publikačního výsledku

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

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

Originální název

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

Anglický název

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

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

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

Rok RIV

2020

Vydáno

12.05.2019

Nakladatel

IEEE Signal Processing Society

Místo

Brighton

ISBN

978-1-5386-4658-8

Kniha

Proceedings of ICASSP

Strany od

6096

Strany do

6100

Strany počet

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"
}

Dokumenty

inaguma_icassp2019_0006096