Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing
This addresses the challenge of isochrony in automatic dubbing for video localization, but it is incremental as it builds on existing methods.
The paper tackled the problem of generating target language speech that aligns with the original video timing in automatic dubbing, and the result was a system that better matches speech timing compared to prior work while simplifying architecture.
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.