arxivst stuff from arxiv that you should probably bookmark

End-to-End MAP Training of a Hybrid HMM-DNN Model

Abstract · Mar 30, 2017 08:40 ·

cs-lg cs-cl cs-ne

Arxiv Abstract

  • Lior Fritz
  • David Burshtein

An hybrid of a hidden Markov model (HMM) and a deep neural network (DNN) is considered. End-to-end training using gradient descent is suggested, similarly to the training of connectionist temporal classification (CTC). We use a maximum a-posteriori (MAP) criterion with a simple language model in the training stage, and a standard HMM decoder without approximations. Recognition results are presented using speech databases. Our method compares favorably to CTC in terms of performance, robustness and quality of alignments.

Read the paper (pdf) »