2026-04-13T14:11:59Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/423802025-12-22T13:46:23Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Öktem, Alp author Farrús, Mireia author Bonafonte Cávez, Antonio author 2019-10-04T09:39:14Z 2019-10-04T09:39:14Z 2019 Comunicació presentada a: Interspeech 2019, celebrat del 15 al 19 setembre de 2019 a Graz, Àustria. 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. Audiovisual translation Dubbing Spoken machine translation Prosody Prosodic phrase alignment for machine dubbing