Gated module neural network for multilingual speech recognition

Yuan Fu Liao, Matus Pleva, Daniel Hladek, Jan Stas, Peter Viszlay, Martin Lojka, Jozef Juhar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

For most multilingual large vocabulary continuous speech recognition (LVCSR) systems, when multiple languages are allowed at the same time, their performance will degrade significantly due to the strong inter-language competition in the decoding phase. To increase the inter-language discrimination capacity, this paper presents a gated module neural network (GMN) approach that adapts a language identification (LID) component to directly assist the final multilingual LVCSR goal. Thanks to an international collaboration 3 large-scale speech corpora (Mandarin, English and Slovak, denoted as Zh, En and Sk) were shared for studying this problem. Hence the proposed approach was evaluated on both bilingual (Zh/En and Sk/En) and trilingual (Zh/En/Sk) LVCSR tasks. The experimental results show that the proposed GMN is promising and the performance of multilingual LVCSRs are now more comparable with the monolingual ones.

Original languageEnglish
Title of host publication2018 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages131-135
Number of pages5
ISBN (Electronic)9781538656273
DOIs
StatePublished - 2 Jul 2018
Event11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Taipei, Taiwan
Duration: 26 Nov 201829 Nov 2018

Publication series

Name2018 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Proceedings

Conference

Conference11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018
Country/TerritoryTaiwan
CityTaipei
Period26/11/1829/11/18

Keywords

  • Gated module neural networks
  • Language identification
  • Multilingual speech recognition

Fingerprint

Dive into the research topics of 'Gated module neural network for multilingual speech recognition'. Together they form a unique fingerprint.

Cite this