Prosodic Phrase Alignment for Machine Dubbing
This addresses the challenge of visual coherence in audiovisual translation for media localization, though it appears incremental as it builds on existing neural machine translation and synthesis methods.
The paper tackles the problem of prosodic phrase synchronization in machine dubbing to align dubbed recordings with lip movements, achieving a speech rate ratio comparable to professional dubbing and improved lip-syncing for long dialogue lines.
Dubbing is a type of audiovisual translation where dialogues are translated and enacted so that they give the impression that the media is in the target language. It requires a careful alignment of dubbed recordings with the lip movements of performers in order to achieve visual coherence. In this paper, we deal with the specific problem of prosodic phrase synchronization within the framework of machine dubbing. Our methodology exploits the attention mechanism output in neural machine translation to find plausible phrasing for the translated dialogue lines and then uses them to condition their synthesis. Our initial work in this field records comparable speech rate ratio to professional dubbing translation, and improvement in terms of lip-syncing of long dialogue lines.