all AI news
Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages. (arXiv:2211.01338v1 [eess.AS])
cs.CL updates on arXiv.org arxiv.org
Cross-lingual dubbing of lecture videos requires the transcription of the
original audio, correction and removal of disfluencies, domain term discovery,
text-to-text translation into the target language, chunking of text using
target language rhythm, text-to-speech synthesis followed by isochronous
lipsyncing to the original video. This task becomes challenging when the source
and target languages belong to different language families, resulting in
differences in generated audio duration. This is further compounded by the
original speaker's rhythm, especially for extempore speech. This paper …
arxiv cross-lingual dubbing pipeline scale technology videos