A many-to-one phone mapping approach for cross-lingual speech recognition

Van Hai Do, Nancy F. Chen, Boon Pang Lim, Mark Hasegawa-Johnson

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

Abstract

This paper presents a novel method for acoustic modeling of an under-resourced language by 'mapping' from acoustic models of well-resourced languages. The proposed method can be considered as a 'many-to-one mapping' method where one speech unit in the target language is built as a linear combination of the source speech unit models and hence we can explicitly observe the relationship of the source language and target language phones. Experiments conducted on the WSJO task show that the proposed method can obtain a much higher performance over the other phone mapping methods.

Original languageEnglish (US)
Title of host publication2016 IEEE RIVF International Conference on Computing and Communication Technologies
Subtitle of host publicationResearch, Innovation, and Vision for the Future, RIVF 2016 - Proceedings
EditorsYo-Sung Ho, Tru Cao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages120-124
Number of pages5
ISBN (Electronic)9781509041336
DOIs
StatePublished - Dec 27 2016
Event12th IEEE RIVF International Conference on Computing and Communication Technologies: Research, Innovation, and Vision for the Future, RIVF 2016 - Hanoi, Viet Nam
Duration: Nov 7 2016Nov 9 2016

Publication series

Name2016 IEEE RIVF International Conference on Computing and Communication Technologies: Research, Innovation, and Vision for the Future, RIVF 2016 - Proceedings

Other

Other12th IEEE RIVF International Conference on Computing and Communication Technologies: Research, Innovation, and Vision for the Future, RIVF 2016
Country/TerritoryViet Nam
CityHanoi
Period11/7/1611/9/16

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'A many-to-one phone mapping approach for cross-lingual speech recognition'. Together they form a unique fingerprint.

Cite this