E2E-V2SResNet: Deep residual convolutional neural networks for end-to-end video driven speech synthesis
Nasir Saleem, Jiechao Gao, Muhammad Irfan, Elena Verdú, Javier Parra Fuente
Topics & Concepts
Computer scienceSpeech recognitionTIMITIntelligibility (philosophy)Convolutional neural networkSpectrogramEncoderResidualLanguage modelArtificial intelligenceHidden Markov modelAlgorithmOperating systemPhilosophyEpistemologySpeech and Audio ProcessingSpeech Recognition and SynthesisMusic and Audio Processing