Audio-driven speech animation using recurrent neutral network

Slim Ouni (1) , Théo Biasutto--Lervat (1) , Sara Dahmani (1)

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Traitement du signal et de l'image [eess.SP]; Linguistique; Sciences de l'information et de la communication; Machine Learning [stat.ML]; Informatique; Multimédia [cs.MM]

Slim Ouni, Théo Biasutto--Lervat, Sara Dahmani. Audio-driven speech animation using recurrent neutral network. United States, Patent n° : WO2021023861. 2021. ⟨hal-03167213⟩