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.
@article{arxiv.2506.00740,
title = {Length Aware Speech Translation for Video Dubbing},
author = {Harveen Singh Chadha and Aswin Shanmugam Subramanian and Vikas Joshi and Shubham Bansal and Jian Xue and Rupeshkumar Mehta and Jinyu Li},
journal= {arXiv preprint arXiv:2506.00740},
year = {2025}
}