Expression-tailored talking face generation with adaptive cross-modal weighting
Dan Zeng, Shuaitao Zhao, Junjie Zhang, Han Liu, Kai Li
Topics & Concepts
Computer scienceExpression (computer science)WeightingArtificial intelligenceAutoencoderDiscriminatorIdentity (music)Computer visionFacial expressionFace (sociological concept)EncoderSpeech recognitionPattern recognition (psychology)Key frameFrame (networking)Artificial neural networkDetectorOperating systemRadiologySocial sciencePhysicsMedicineProgramming languageAcousticsSociologyTelecommunicationsFace recognition and analysisSpeech and Audio ProcessingGenerative Adversarial Networks and Image Synthesis