A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training (2021)

First Author: Haider A
Attributed to:  Natural Speech Technology funded by EPSRC

Abstract

No abstract provided

Bibliographic Information

Digital Object Identifier: http://dx.doi.org/10.48550/arxiv.2103.07554

Publication URI: https://arxiv.org/abs/2103.07554

Type: Preprint