Natural language processing with neural networks


The example shown here is the subject of current research in the field of language technology. Scientists are currently still investigating questions such as: Which weighing of the individual factors, such as translation quality and synchronization quality, optimizes the overall quality? At which point exactly do people even notice that the lip-sync is no longer perfect?

It is also important to remember that world languages vary considerably. Consequently, this problem is so complex that a single model cannot do justice to it. As a result, it is essential to train separate models for the different pairs of languages to be translated.


  1. "Computing Machinery and Intelligence" by A.M. Turing, Mind, volume LIX, October 1950, pp. 443-460,
  2. Karpathy (2015);

The Author

Timo Baumann is Professor of Artificial Intelligence at the Faculty of Computer Science and Mathematics at OTH Regensburg where he focuses on natural language processing. His research focuses on socially and interactively adequate conversational agents, prosody processing, and automatic lip-synchronous dubbing. Christian Schuler is currently studying computer science in the Master of Science program at the University of Hamburg. His bachelor thesis was about the acquisition of perceived quality of lip synchronicity in audiovisually translated material.

Buy this article as PDF

Express-Checkout as PDF
Price $2.95
(incl. VAT)

Buy Linux Magazine

Get it on Google Play

US / Canada

Get it on Google Play

UK / Australia

Related content

  • Neural Networks

    3, 4, 8, 11… ? A neural network can complete this series without knowledge of the underlying algorithm – by a kind of virtual gut feeling. We’ll show you how neural networks solve problems by simulating the behavior of a human brain.

  • Free Software Projects

    Even hardened nerds are often over-challenged by the less than intuitive field of statistics. Besides the theory, you need to know how to use the software that converts all the theory into a practical application.

  • FAQ

    Welcome our new artificial intelligence overlords by tinkering with their gray matter.

  • Spam-Detecting Neural Network

    Build a neural network that uncovers spam websites.

  • Neural networks learn from mistakes and remember successes

    The well-known Monty Hall game show problem can be a rewarding maiden voyage for prospective statisticians. But is it possible to teach a neural network to choose between goats and cars with a few practice sessions?

comments powered by Disqus
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters

Support Our Work

Linux Magazine content is made possible with support from readers like you. Please consider contributing when you’ve found an article to be beneficial.

Learn More