Revisiting Hybrid and GMM-HMM system combination techniques

Pawel Swietojanski, Arnab Ghoshal, Steve Renals

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages6744-6748
Number of pages5
ISBN (Print)978-1-4799-0356-6
DOIs
Publication statusPublished - 2013

Fingerprint Dive into the research topics of 'Revisiting Hybrid and GMM-HMM system combination techniques'. Together they form a unique fingerprint.

Cite this