English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Video dubbing aims to translate the original speech in a film or televisionprogram into the speech in a target language, which can be achieved with acascaded system consisting of speech recognition, machine translation andspeech synthesis. To ensure the translated speech to be well aligned with thecorresponding video, the length/duration of the translated speech should be asclose as possible to that of the original speech, which requires strict lengthcontrol. Previous works usually control the number of words or charactersgenerated by the machine translation model to be similar to the sourcesentence, without considering the isochronicity of speech as the speechduration of words/characters in different languages varies. In this paper, wepropose a machine translation system tailored for the task of video dubbing,which directly considers the speech duration of each token in translation, tomatch the length of source and target speech. Specifically, we control thespeech length of generated sentence by guiding the prediction of each word withthe duration information, including the speech duration of itself as well ashow much duration is left for the remaining words. We design experiments onfour language directions (German -> English, Spanish -> English, Chinese <->English), and the results show that the proposed method achieves better lengthcontrol ability on the generated speech than baseline methods. To make up thelack of real-world datasets, we also construct a real-world test set collectedfrom films to provide comprehensive evaluations on the video dubbing task.

VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing