Score: 1

Length Aware Speech Translation for Video Dubbing

Published: May 31, 2025 | arXiv ID: 2506.00740v1

By: Harveen Singh Chadha , Aswin Shanmugam Subramanian , Vikas Joshi and more

BigTech Affiliations: Microsoft

Potential Business Impact:

Makes dubbed movie voices match the talking.

Business Areas:
Translation Service Professional Services

In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video dubbing scenarios. We developed a phoneme-based end-to-end length-sensitive speech translation (LSST) model, which generates translations of varying lengths short, normal, and long using predefined tags. Additionally, we introduced length-aware beam search (LABS), an efficient approach to generate translations of different lengths in a single decoding pass. This approach maintained comparable BLEU scores compared to a baseline without length awareness while significantly enhancing synchronization quality between source and target audio, achieving a mean opinion score (MOS) gain of 0.34 for Spanish and 0.65 for Korean, respectively.

Country of Origin
🇺🇸 United States

Page Count
5 pages

Category
Computer Science:
Computation and Language