Usefulness of Emotional Prosody in Neural Machine Translation

arXiv:2404.17968v1 Announce Type: cross
Abstract: Neural Machine Translation (NMT) is the task of translating a text from one language to another with the use of a trained neural network. Several existing works aim at incorporating external information into NMT models to improve or control predicted translations (e.g. sentiment, politeness, gender). In this work, we propose to improve translation quality by adding another external source of information: the automatically recognized emotion in the voice. This work is motivated by the assumption …

abstract aim arxiv control cs.cl cs.lg cs.sd eess.as gender information language machine machine translation network neural machine translation neural network sentiment text translation translations type