English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep Neural Network (DNN) acoustic models often use discriminative sequencetraining that optimises an objective function that better approximates the worderror rate (WER) than frame-based training. Sequence training is normallyimplemented using Stochastic Gradient Descent (SGD) or Hessian Free (HF)training. This paper proposes an alternative batch style optimisation frameworkthat employs a Natural Gradient (NG) approach to traverse through the parameterspace. By correcting the gradient according to the local curvature of theKL-divergence, the NG optimisation process converges more quickly than HF.Furthermore, the proposed NG approach can be applied to any sequencediscriminative training criterion. The efficacy of the NG method is shown usingexperiments on a Multi-Genre Broadcast (MGB) transcription task thatdemonstrates both the computational efficiency and the accuracy of theresulting DNN models.

Sequence Training of DNN Acoustic Models With Natural Gradient