Revisiting hybrid and GMM-HMM system combination techniques

  • Swietojanski P
  • Ghoshal A
  • Renals S
  • 12


    Mendeley users who have this article in their library.
  • 23


    Citations of this article.


In this paper we investigate techniques to combine hybrid HMM-DNN (hidden Markov model - deep neural network) and tandem HMM-GMM (hidden Markov model - Gaussian mixture model) acoustic models using: (1) model averaging, and (2) lattice combination with Minimum Bayes Risk decoding. We have performed experiments on the “TED Talks” task following the protocol of the IWSLT-2012 evaluation. Our experimental results suggest that DNN-based and GMM-based acoustic models are complementary, with error rates being reduced by up to 8% relative when the DNN and GMM systems are combined at model-level in a multi-pass automatic speech recognition (ASR) system. Additionally, further gains were obtained by combining model-averaged lattices with the one obtained from baseline systems.

Author-supplied keywords

  • TED
  • deep neural networks
  • hybrid
  • system combination
  • tandem

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text


  • Pawel Swietojanski

  • Arnab Ghoshal

  • Steve Renals

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free