Header menu link for other important links
X
Investigation of different acoustic modeling techniques for low resource Indian language data
Published in Institute of Electrical and Electronics Engineers Inc.
2015
Abstract
In this paper, we investigate the performance of deep neural network (DNN) and Subspace Gaussian mixture model (SGMM) in low-resource condition. Even though DNN outperforms SGMM and continuous density hidden Markov models (CDHMM) for high-resource data, it degrades in performance while modeling low-resource data. Our experimental results show that SGMM outperforms DNN for limited transcribed data. To resolve this problem in DNN, we propose to train DNN containing bottleneck layer in two stages: First stage involves extraction of bottleneck features. In second stage, the extracted bottleneck features from first stage are used to train DNN having bottleneck layer. All our experiments are performed using two Indian languages (Tamil & Hindi) in Mandi database. Our proposed method shows improved performance when compared to baseline SGMM and DNN models for limited training data. © 2015 IEEE.
About the journal
JournalData powered by Typeset2015 21st National Conference on Communications, NCC 2015
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
Open AccessNo
Concepts (12)
  •  related image
    Computational linguistics
  •  related image
    Hidden markov models
  •  related image
    Markov processes
  •  related image
    Trellis codes
  •  related image
    BOTTLENECK
  •  related image
    DNN
  •  related image
    Hindi
  •  related image
    Indian languages
  •  related image
    LOW RESOURCE DATA
  •  related image
    SGMM
  •  related image
    Tamil
  •  related image
    Modeling languages