2023/02/25 by Alexandra Chronopoulou, Brian J. Thompson, Chronopoulou, Alexandra +9
Arts and Humanities · Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Handwritten Text Recognition Techniques #Multimodal Machine Learning Applications #Sound (cs.SD) #Subtitles and Audiovisual Media #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2302.12979
openalex publication_date 2023/02/25 · openalex created_date 2023/03/03 · openalex updated_date 2026/07/28
Automatic dubbing (AD) is the task of translating the original speech in a video into target language speech. The new target language speech should satisfy isochrony; that is, the new speech should be time aligned with the original video, including mouth movements, pauses, hand gestures, etc. In this paper, we propose training a model that directly optimizes both the translation as well as the speech duration of the generated translations. We show that this system generates speech that better matches the timing of the original speech, compared to prior work, while simplifying the system architecture.