Face2Speech: Towards Multi-Speaker Text-to-Speech Synthesis Using an Embedding Vector Predicted from a Face Image
Shunsuke Goto, Kotaro Onishi, Yuki Saito, Kentaro Tachibana, Koichiro Mori
Topics & Concepts
Computer scienceEmbeddingSpeech recognitionFace (sociological concept)Artificial intelligenceSpeech synthesisImage (mathematics)Speaker recognitionLinguisticsPhilosophySpeech Recognition and SynthesisFace recognition and analysisSpeech and Audio Processing