Sound-to-Imagination: Unsupervised Crossmodal Translation Using Deep Dense Network Architecture.
Leonardo A. FanzeresCliment NadeuPublished in: CoRR (2021)
Keyphrases
- network architecture
- artificial neural
- neural network
- deep architectures
- unsupervised learning
- network design
- machine translation
- data driven
- weakly supervised
- unsupervised manner
- cross language information retrieval
- supervised learning
- deep learning
- connection weights
- semi supervised
- neural network model
- stereo correspondence
- network infrastructure
- data sets
- deep belief networks
- artificial neural networks
- voice over ip