Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks.
Amanda Cardoso DuarteFrancisco RoldanMiquel TubauJanna EscurSantiago PascualAmaia SalvadorEva MohedanoKevin McGuinnessJordi TorresXavier Giró-i-NietoPublished in: ICASSP (2019)
Keyphrases
- recognition engine
- human faces
- facial expressions
- generative model
- network structure
- audio visual
- computer networks
- unsupervised learning
- data driven
- social networks
- hidden markov models
- network topologies
- speech synthesis
- multi agent
- pattern recognition
- automatic speech recognition
- heterogeneous networks
- spontaneous speech