Automated Speech Translation: Challenges, Approaches and Research Directions
Jan Niehues (Karlsruhe Institute of Technology)
In today’s globalized world, we have the opportunity to communicate with people all over the world. However, often the language barrier still poses a challenge and prevents communication. Machines that automatically translate the speech from one language into another are a long dream of humankind.
In this presentation, we want to review the current state of the art in automated speech translation. We will start by discussing the challenges of speech translation with a special focus on the aspects that are hard for computers. We will continue with a review of state-of-the-art methods to build speech translation systems. In the final part of the presentation, we will highlight several research directions of simultaneous speech translation: latency, sentence segmentation and stream decoding as well as present techniques that address these challenges.