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. © 2013 IEEE.
CITATION STYLE
Swietojanski, P., Ghoshal, A., & Renals, S. (2013). Revisiting hybrid and GMM-HMM system combination techniques. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 6744–6748). https://doi.org/10.1109/ICASSP.2013.6638967
Mendeley helps you to discover research relevant for your work.