PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing
2026-04-10 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed a method to improve automated dubbing by making dubbed speech better match the original video's timing and lip movements. Their approach first adjusts the translated text so the spoken words last as long as the original, then changes the speech sounds to better match lip movements using vowel similarities. They also created a version called PS-Comet that keeps the meaning intact while syncing lips better. Testing on multiple languages showed their methods outperform standard text-to-speech and even professional voice actors in syncing and meaning preservation.
automated dubbingtext-to-speech (TTS)lip synchronizationisochronyphonetic synchronizationdynamic time warping (DTW)paraphrasingsemantic similaritycross-linguistic dubbing
Authors
Changi Hong, Yoonah Song, Hwayoung Park, Chaewoon Bang, Dayeon Gu, Do Hyun Lee, Hong Kook Kim
Abstract
Recently, artificial intelligence-based dubbing technology has advanced, enabling automated dubbing (AD) to convert the source speech of a video into target speech in different languages. However, natural AD still faces synchronization challenges such as duration and lip-synchronization (lip-sync), which are crucial for preserving the viewer experience. Therefore, this paper proposes a synchronization method for AD processes that paraphrases translated text, comprising two steps: isochrony for timing constraints and phonetic synchronization (PS) to preserve lip-sync. First, we achieve isochrony by paraphrasing the translated text with a language model, ensuring the target speech duration matches that of the source speech. Second, we introduce PS, which employs dynamic time warping (DTW) with local costs of vowel distances measured from training data so that the target text composes vowels with pronunciations similar to source vowels. Third, we extend this approach to PSComet, which jointly considers semantic and phonetic similarity to preserve meaning better. The proposed methods are incorporated into text-to-speech systems, PS-TTS and PS-Comet TTS. The performance evaluation using Korean and English lip-reading datasets and a voice-actor dubbing dataset demonstrates that both systems outperform TTS without PS on several objective metrics and outperform voice actors in Korean-to-English and English-to-Korean dubbing. We extend the experiments to French, testing all pairs among these languages to evaluate cross-linguistic applicability. Across all language pairs, PS-Comet performed best, balancing lip-sync accuracy with semantic preservation, confirming that PS-Comet achieves more accurate lip-sync with semantic preservation than PS alone.