Loading...

Flat-Start single-stage discriminatively trained hmm-based models for asr

Hadian, H ; Sharif University of Technology | 2018

563 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TASLP.2018.2848701
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2018
  4. Abstract:
  5. In recent years, end-to-end approaches to automatic speech recognition have received considerable attention as they are much faster in terms of preparing resources. However, conventional multistage approaches, which rely on a pipeline of training hidden Markov models (HMM)-GMM models and tree-building steps still give the state-of-the-art results on most databases. In this study, we investigate flat-start one-stage training of neural networks using lattice-free maximum mutual information (LF-MMI) objective function with HMM for large vocabulary continuous speech recognition. We thoroughly look into different issues that arise in such a setup and propose a standalone system, which achieves word error rates (WER) comparable with that of the state-of-the-art multi-stage systems while being much faster to prepare. We propose to use full biphones to enable flat-start context-dependent (CD) modeling and show through experiments that our CD modeling approach can be almost as effective as regular tree-based CD modeling. We show that our flat-start LF-MMI setup together with this tree-free CD modeling technique achieves 10 to 25 % relative WER reduction compared to other end-to-end methods on well-known databases. The improvements are larger for smaller databases. © 2014 IEEE
  6. Keywords:
  7. Flat-start ; Hidden Markov models ; Single-stage ; Continuous speech recognition ; Database systems ; Stereophonic broadcasting ; Automatic speech recognition ; Large vocabulary continuous speech recognition ; Lattice-free ; Maximum mutual information ; Multistage approach ; Objective functions ; Single stage ; Standalone systems ; Hidden Markov models
  8. Source: IEEE/ACM Transactions on Audio Speech and Language Processing ; Volume 26, Issue 11 , 2018 , Pages 1949-1961 ; 23299290 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/8387866