Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion

Hirofumi Inaguma, Jaejin Cho, Murali Karthick Baskar, Tatsuya Kawahara, Shinji Watanabe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This work explores better adaptation methods to low-resource languages using an external language model (LM) under the framework of transfer learning. We first build a language-independent ASR system in a unified sequence-to-sequence (S2S) architecture with a shared vocabulary among all languages. During adaptation, we perform LM fusion transfer, where an external LM is integrated into the decoder network of the attention-based S2S model in the whole adaptation stage, to effectively incorporate linguistic context of the target language. We also investigate various seed models for transfer learning. Experimental evaluations using the IARPA BABEL data set show that LM fusion transfer improves performances on all target five languages compared with simple transfer learning when the external text data is available. Our final system drastically reduces the performance gap from the hybrid systems.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6096-6100
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 2019 May
Externally publishedYes
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 2019 May 122019 May 17

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period19/5/1219/5/17

Keywords

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

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion'. Together they form a unique fingerprint.

  • Cite this

    Inaguma, H., Cho, J., Baskar, M. K., Kawahara, T., & Watanabe, S. (2019). Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 6096-6100). [8682918] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682918