Length Aware Speech Translation for Video Dubbing
By: Harveen Singh Chadha , Aswin Shanmugam Subramanian , Vikas Joshi and more
Potential Business Impact:
Makes dubbed movie voices match the talking.
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.
Similar Papers
Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
Sound
Makes dubbed videos match the original speaking time.
BLAB: Brutally Long Audio Bench
Artificial Intelligence
Tests if computers can understand long conversations.
Long-Video Audio Synthesis with Multi-Agent Collaboration
CV and Pattern Recognition
Makes movies talk with matching voices.