Synthesizing Talking Faces from Text and Audio: An Autoencoder and Sequence-to-Sequence Convolutional Neural Network
Na Liu, Tao Zhou, Yunfeng Ji, Ziyi Zhao, Lihong Wan
Topics & Concepts
Computer scienceAutoencoderFace (sociological concept)ENCODESequence (biology)Convolutional neural networkLandmarkArtificial intelligenceSpeech recognitionRepresentation (politics)syncEncoderComputer visionPipeline (software)Pattern recognition (psychology)Artificial neural networkFrame (networking)BiochemistryOperating systemSocial scienceGeneChemistryProgramming languageLawSociologyPoliticsBiologyTelecommunicationsGeneticsPolitical scienceFace recognition and analysisSpeech and Audio ProcessingGenerative Adversarial Networks and Image Synthesis