WAV2PIX: Speech-conditioned Face Generation using Generative Adversarial Networks.
Amanda Cardoso DuarteFrancisco RoldanMiquel TubauJanna EscurSantiago PascualAmaia SalvadorEva MohedanoKevin McGuinnessJordi TorresXavier Giró-i-NietoPublished in: CVPR Workshops (2019)
Keyphrases
- recognition engine
- speech recognition
- social networks
- network design
- speech signal
- recognition algorithm
- audio visual
- generative model
- unsupervised learning
- facial features
- network structure
- human faces
- multi agent
- neural network
- computer networks
- data driven
- face images
- automatic speech recognition
- facial expressions
- face verification
- spoken language
- network size
- endpoint detection