skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Multilingual Data Selection for Low Resource Speech Recognition

Approved For Public Release

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Multilingual Data Selection for Low Resource Speech Recognition
  • Author: Thomas, Samuel ; Audhkhasi,Kartik ; Cui,Jia ; Kingsbury,Brian ; Ramabhadran,Bhuvana
  • Subjects: acoustic models ; deep neural networks ; IARPA Collection ; low resource speech recognition ; multilingual features
  • Description: Feature representations extracted from deep neural network-based multilingual frontends provide significant improvements to speech recognition systems in low resource settings. To effectively train these frontends, we introduce a data selection technique that discovers language groups from an available set of training languages. This data selection method reduces the required amount of training data and training time by approximately 40 , with minimal performance degradation. We present speech recognition results on 7 very limited language pack (VLLP) languages from the second option period of the IARPA Babel program using multilingual features trained on up to 10 languages. The proposed multilingual features provide up to 15 relative improvement over baseline acoustic features on the VLLP languages. INTERSPEECH 2016 , 08 Sep 2016, 12 Sep 2016, Published in INTERSPEECH 2016, p. 3853-3857, ISBN 9781510833135
  • Creation Date: 2016
  • Language: English
  • Source: DTIC Technical Reports
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait