Neural Speech Translation at AppTek
Evgeny Matusov, Patrick Wilken, Parnia Bahar, Julian Schamper, Pavel Golik, Albert Zeyer, Joan Albert Silvestre-Cerda, Adrià Martínez-Villaronga, Hendrik Pesch, Jan-Thorsten Peter
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
This work describes AppTek’s speech translation pipeline that includes strong state-of-the-art automatic speech recognition (ASR) and neural machine translation (NMT) components. We show how these components can be tightly coupled by encoding ASR confusion networks, as well as ASR-like noise adaptation, vocabulary normalization, and implicit punctuation prediction during translation. In another experimental setup, we propose a direct speech translation approach that can be scaled to translation tasks with large amounts of text-only parallel training data but a limited number of hours of recorded and human-translated speech.