Georg Heigold

A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture

2015

This article proposes and evaluates a Gaussian Mixture Model (GMM) represented as the last layer of a Deep Neural Network (DNN) architecture and jointly optimized with all previous layers using Asynchronous Stochastic Gradient Descent (ASGD). …

End-to-end text-dependent speaker verification

2016

In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components …

A Linguistic Evaluation of Rule-Based, Phrase-Based, and Neural MT Engines

2017 · ˜The œPrague Bulletin of Mathematical Linguistics

Abstract In this paper, we report an analysis of the strengths and weaknesses of several Machine Translation (MT) engines implementing the three most widely used paradigms. The analysis is based on a manually built test …