Header menu link for other important links
Improved acoustic modeling of low-resource languages using shared SGMM parameters of high-resource languages
Published in Institute of Electrical and Electronics Engineers Inc.
In this paper, we investigate methods to improve the recognition performance of low-resource languages with limited training data by borrowing subspace parameters from a high-resource language in subspace Gaussian mixture model (SGMM) framework. As a first step, only the state-specific vectors are updated using low-resource language, while retaining all the globally shared parameters from the high-resource language. This approach gave improvements only in some cases. However, when both state-specific and weight projection vectors are re-estimated with low-resource language, we get consistent improvement in performance over conventional monolingual SGMM of the low-resource language. Further, we conducted experiments to investigate the effect of different shared parameters on the acoustic model built using the proposed method. Experiments were done on the Tamil, Hindi and Bengali corpus of MANDI database. Relative improvement of 16.17% for Tamil, 13.74% for Hindi and 12.5% for Bengali, over respective monolingual SGMM were obtained. © 2016 IEEE.
About the journal
JournalData powered by Typeset2016 22nd National Conference on Communication, NCC 2016
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
Open AccessNo
Concepts (8)
  •  related image
    Gaussian distribution
  •  related image
  •  related image
    Acoustic model
  •  related image
  •  related image
    Indian languages
  •  related image
  •  related image
  •  related image
    Modeling languages